Software Engineer - Codex Core Agents

About Our TeamThe Codex Core Agent team is responsible for developing the foundational kernel of Codex. We focus on enhancing the agent's capabilities, expediting research, and ensuring these advancements translate into practical applications for our users.This entails collaboration across the various systems that allow Codex to function effectively in real-world scenarios, including optimizing production performance, managing token usage, minimizing latency, ensuring reliability, controlling costs, and scaling capacity. We also work on the core execution loop and interfaces that transform models into practical actions, alongside building infrastructure that supports other teams in leveraging Codex. Importantly, our feedback systems utilize real-world usage to refine models and enhance agent performance over time.About the RoleWe are seeking talented applied AI engineers to help transition Codex agents from impressive demonstrations to reliable, everyday tools. This position involves enhancing agent performance on actual software engineering tasks and bridging the gap between research capabilities and tangible real-world utility.You will collaborate closely with research teams, infrastructure, and product development to ensure that agents are not only powerful but also practical, controllable, and dependable. Your mission is to not only enhance model performance in isolation but also to translate those improvements into measurable increases in solution rates, usability, and economic value for our users.Your ResponsibilitiesDesign and refine agent behaviors across real-world coding tasks and extended workflows.Collaborate with research to create and execute evaluations that measure agent performance, identify regressions, and understand failure modes and edge cases.Enhance performance through effective prompting, strategic tool usage, context construction, and model-facing experimentation.Investigate production failures and systematically enhance stability and reliability.Develop feedback loops and data systems that integrate real-task data into our evaluation and research processes.Collaborate with product teams to shape user-facing agent experiences and the essential interfaces that support agent functions.Help define the criteria for what constitutes successful completion of complex tasks by agents.Ideal Candidate ProfileExperience in building or deploying machine learning or LLM-powered products.Proficiency in Python and familiarity with modern machine learning tools.Background in model evaluation, fine-tuning, or related areas.

About Our TeamJoin the Codex Deployment Engineering team at OpenAI, where we empower organizations to seamlessly integrate advanced coding tools throughout their software development lifecycle. We are more than technical partners; we are collaborators who accelerate the planning, building, and delivery of software for a diverse range of clients, from innovative startups to established global enterprises.About the RoleWe are on the lookout for a technically proficient and creatively inclined AI Deployment Engineer who is not just a user of AI coding tools but is passionate about enhancing developer productivity. In this role, you will work closely with engineering leaders and hands-on developers to create, validate, and expand advanced AI workflows. You will often leverage Codex to develop prototypes, demos, integrations, and automations that our customers will utilize.This multifaceted position blends technical architecture, product strategy, and customer engagement. Collaborating with Sales, Solutions Engineering, Product Management, Applied Engineering, and the broader Codex team, you will advocate for customer needs, influence product direction, and facilitate the successful deployment of intelligent coding systems across some of the most impactful companies worldwide.Key Responsibilities:Act as the primary technical expert on OpenAI Codex for a select group of clients, working closely with their engineering teams to enhance coding workflows.Collaborate with customers to design and implement AI-powered development workflows, from rapid prototyping to scalable production.Create high-quality demos, reference implementations, and workflow automations using Codex in your development process.Facilitate large-scale workshops, in-depth technical sessions, and hands-on training that empower engineering teams to adopt AI coding tools effectively and safely.Contribute technical content such as examples, guides, patterns, and best practices to the OpenAI Cookbook, helping the broader developer community enhance their use of Codex.Gather valuable insights from actual customer deployments and translate them into actionable product proposals and feedback for internal teams.Influence customer strategies and decision-making by illustrating how AI coding tools enhance their software development lifecycle (SDLC), technical roadmap, and organizational goals.

Join OpenAI as a Manager of AI Deployment Engineering for our Codex team. In this pivotal role, you will lead initiatives to deploy cutting-edge AI technologies, ensuring efficient integration and transformative impact across various platforms. Your expertise will drive the development of innovative solutions that enhance user experiences and streamline operations.

Join Our Innovative Team at ArcadeAt Arcade, we are revolutionizing the way physical products are created with our cutting-edge AI platform. We empower individuals to turn their creative ideas into tangible products seamlessly, utilizing natural language and generative AI. Our mission is to democratize product design, making it as effortless as sharing a post online.Backed by a remarkable $42M in funding from industry-leading investors including Reid Hoffman and Ashton Kutcher, our company is a rising star in the tech landscape. Guided by our founder Mariam Naficy and a team steeped in AI and design expertise, we are at the forefront of a new frontier that merges AI, personal expression, and on-demand manufacturing.Your Role as an Applied AI EngineerWe are on the lookout for an Applied AI Engineer to enhance our generative AI capabilities. This position combines hands-on model development with the integration of advanced AI techniques into our production systems. You will collaborate with diverse teams to conduct research, experiment with models, and implement AI-driven products.

About Our TeamThe Codex team at OpenAI is at the forefront of creating cutting-edge AI systems designed to empower users by writing code, understanding software logic, and functioning as intelligent agents for both developers and non-developers. Our mission is to redefine the landscape of code generation and intelligent reasoning, deploying these innovations into real-world applications such as ChatGPT and our API, as well as future tools tailored for intelligent coding. We engage deeply in research, engineering, product development, and infrastructure management, overseeing the entire lifecycle of experimentation, deployment, and iterative improvements on advanced coding functionalities.About the PositionAs a key member of the Codex team, you will enhance the capabilities, performance, and reliability of AI coding models through rigorous research, innovative experimentation, and systematic optimization. Collaborating with top-tier researchers and engineers, you will develop and deploy robust systems that enable millions to code more efficiently and effectively, ensuring these systems are not only powerful but also cost-efficient and ready for production.We seek individuals who possess a blend of deep curiosity, strong technical skills, and a commitment to impactful work. Whether your expertise lies in machine learning research, systems engineering, or performance optimization, you will be instrumental in advancing the state-of-the-art and translating these breakthroughs into user-friendly applications.This position is located in San Francisco, CA, and follows a hybrid work model requiring three days per week in the office. We also provide relocation assistance for new hires.In This Role, You Will:Design and conduct experiments aimed at enhancing code generation, reasoning, and agentic behaviors in Codex models.Generate research insights to improve model training, alignment, and evaluation processes.Identify and rectify inefficiencies throughout the Codex system stack—from agent behavior to large language model inference to container orchestration—paving the way for significant performance enhancements. Develop tools to measure, profile, and optimize system performance on a large scale.Collaborate across the technical stack to prototype new features, troubleshoot complex issues, and deliver improvements to production environments.You Will Excel in This Role If You:Are enthusiastic about exploring and advancing the capabilities of large language models, particularly in software reasoning and code generation.Possess robust software engineering skills and enjoy rapidly transforming concepts into functional prototypes.Take a holistic view of performance, effectively balancing speed, efficiency, and quality.

About Our TeamAt OpenAI, the Codex team is on a mission to revolutionize software engineering through cutting-edge AI technology. We are developing an AI software engineer capable of collaboration, task delegation, and proactive engagement. Our dynamic team combines expertise in research, engineering, design, and product development, continuously iterating on the Codex agent's capabilities and training the model to excel in complex software engineering tasks.The Codex team is at the forefront of creating advanced AI systems that can write code, reason about software, and serve as intelligent agents for both developers and non-developers. We manage the complete lifecycle of experimentation, deployment, and enhancement of innovative coding functionalities across research, engineering, product, and infrastructure.Codex for Teams specializes in developing products and platform functionalities that facilitate the integration of Codex into various team settings. Our cross-functional team works across the technological stack to create both engaging product experiences and essential platform capabilities. We cater to a diverse customer base, from small teams to large enterprises, and our mission is pivotal to realizing Codex as a proactive team member.About The RoleAs we expand, our goal is to transform Codex from a robust individual tool into a production-ready teammate for entire organizations. You will collaborate with internal OpenAI teams and external clients, ranging from agile startups to established enterprises, to ensure that Codex can be deployed, operated, and trusted in demanding real-world environments.With the surge in consumer adoption of Codex, enterprise demand is growing swiftly, offering exciting opportunities to enhance workflows, controls, and reliability. This team is dedicated to converting complex, real-world requirements into reliable, scalable product and platform capabilities.You will engage directly with a select group of highly involved design-partner customers, utilizing their actual deployments to identify opportunities and requirements for Codex's success within contemporary engineering organizations. These insights will inform your development work across product, infrastructure, and deployment methodologies for all teams utilizing Codex.This role encompasses end-to-end system ownership, from architecture and implementation to production operations, with a strong emphasis on both quality and speed.In This Role, You Will:Influence the evolution of Codex by understanding how teams utilize (and sometimes challenge) AI-powered software...

About the TeamAt OpenAI, we are pioneering the future of software engineering with Codex, an advanced AI-powered software engineer designed to assist, delegate tasks, and proactively manage future challenges. Our dynamic team blends research, engineering, design, and product expertise to enhance the Codex agent harness and product, ensuring it excels in complex software engineering tasks.The Codex team is dedicated to creating cutting-edge AI systems capable of writing code, reasoning about software, and serving as intelligent assistants for both developers and non-developers. We oversee the complete lifecycle of experimentation, deployment, and refinement of innovative coding capabilities across research, engineering, product, and infrastructure.Codex Cloud is focused on developing cloud-first software engineering products and the essential platform capabilities that enable agentic experiences across OpenAI. This cross-functional team collaborates across the stack to deliver both exceptional product experiences and foundational platform capabilities.About the RoleAs a member of Codex Cloud, you will take ownership of cloud-based agentic experiences, such as code reviews and cloud tasks, alongside the essential runtime/orchestration layer for these tasks. This infrastructure transforms Codex from a code generator into a scalable AI software engineer. It provides secure, sandboxed environments where Codex can execute commands, manage files, run tests, and progressively enhance its output across real codebases—just like a human developer. Furthermore, Codex Runtime serves as the distributed systems foundation that enables numerous supervised AI agents to operate within OpenAI's and clients' data centers, addressing increasingly complex objectives over extended periods. By providing agents with a tangible working context and dependable execution environment, Codex Runtime empowers Codex to validate its modifications, debug errors, and produce production-ready results, defining how AI agents interact safely and reliably with the world's software.Your Responsibilities:Influence the evolution of Codex by analyzing actual user interactions with AI-powered software engineering, driving enhancements across product, infrastructure, and model behavior to establish Codex as a trusted collaborator for organizations.Craft comprehensive customer-facing software engineering experiences for both consumer and enterprise segments, automating and elevating the software development lifecycle.

About UsAt Applied Compute, we are pioneering the development of Specific Intelligence for enterprises, creating agents that continuously learn from a company’s processes, data, expertise, and objectives. Our mission is to bridge the gap between isolated AI capabilities and their effective application within real business environments. Traditional AI systems often fall short as they lack the ability to adapt based on feedback. Our innovative continual learning layer captures context, memory, and decision-making processes across the enterprise, enabling specialized agents to engage in meaningful work.What Excites Us: We operate at the exciting intersection of product development and cutting-edge research. Our product team designs the platform that empowers a new generation of digital coworkers, while our research team drives advancements in post-training and reinforcement learning to enhance user experiences. As an applied research engineer, you will work directly with clients to implement models in production, combining robust product development with deep research insights to facilitate AI integration in enterprises.Meet Our Team: Our diverse team consists of engineers, researchers, and operators, many of whom are former founders. We have previously built reinforcement learning infrastructure at OpenAI, established data foundations at Scale AI, and contributed to significant systems at companies like Together, Two Sigma, and Watershed. We collaborate with Fortune 50 clients, including DoorDash, Mercor, and Cognition, and are proud to be backed by reputable investors such as Benchmark, Sequoia, and Lux.Who Thrives Here: We seek individuals who are passionate about applying innovative research and complex systems to solve real-world challenges. You should feel comfortable navigating new environments rapidly—be it a fresh codebase, a client’s data architecture, or an unfamiliar problem domain. A genuine enjoyment for customer interaction, empathy, and a deep understanding of their operational workflows are essential. Candidates with entrepreneurial backgrounds, extensive side projects, or a proven track record of end-to-end ownership typically excel in our environment.

Join OpenAI’s Codex Team as a Senior Data ScientistAbout Our TeamCodex is an innovative first-party developer product by OpenAI, concentrating on agentic software engineering. Our mission is to create cutting-edge tools that empower engineers to design, write, test, and deploy code more efficiently and safely at scale. We work collaboratively with research and product teams to transform advancements in AI models into significant productivity enhancements for developers.Role OverviewIn the role of Senior Data Scientist at Codex, you will play a crucial part in evaluating and driving product-market fit for our AI-driven developer tools. You will define the metrics of “developer productivity” for our offerings, conduct experiments on new coding models and user experiences, and identify areas where our technology can enhance or hinder performance across various languages and tasks. Your findings will have a direct impact on how the software industry evolves.This position is located in San Francisco, CA, and we follow a hybrid work model requiring 3 days in the office weekly. We also provide relocation assistance for new hires.Your ResponsibilitiesCollaborate closely with the Codex product team to uncover opportunities for enhancing developer outcomes and fostering growth.Design and analyze A/B tests and staged rollouts of new coding models and product features.Establish and implement key performance metrics such as suggestion acceptance rates, edit distances, compile/test pass rates, task completion times, latency, and overall session productivity.Create informative dashboards and analyses that enable the team to independently find answers to product-related questions (segmented by language, framework, repository size, task type).Investigate failure modes and work with Research to identify targeted improvements (model quality signals, user feedback, evaluations).Ideal Candidate Profile5+ years of experience in a quantitative role within a developer-focused or high-growth product environment.Proficiency in SQL and Python, with a solid understanding of experimental design and causal inference methodologies.Demonstrated experience in defining product metrics that relate to user value.Strong communication skills to effectively engage with product managers, engineers, and designers, and influence product direction.Preferred QualificationsA robust programming background with the ability to prototype, run simulations, and assess code quality.Familiarity with IDE/extension telemetry or analytics related to developer tooling.Previous experience with Natural Language Processing (NLP), Large Language Models (LLMs), or code models is a plus.

Quizlet Inc. is looking for an Applied AI Engineer to create AI-driven features that support student learning. This position centers on developing and deploying machine learning solutions aimed at making study experiences more effective and engaging for a global user base. What you will do Design and implement machine learning models to enhance Quizlet’s educational tools Work on features that help students study more efficiently and enjoyably Locations Denver, CO New York, NY San Francisco, CA Seattle, WA

Join the Visionaries at Automat!At Automat, we are a collective of innovative technologists hailing from prestigious backgrounds at Google Creative Lab and Samsung’s innovation Think Tank. Our mission is to transform the future of business through intelligent agents that enhance operational efficiency and eventually manage enterprises autonomously. We are leaders in redefining Enterprise AI Agents and Intelligent Document Processing, creating cutting-edge tools and infrastructure to seamlessly integrate AI advancements into practical applications.We cherish curiosity, teamwork, and impactful contributions over strict credentials. If you are passionate about AI and automation, excel in dynamic and creative settings, and yearn to engage in groundbreaking projects, we invite you to apply!While this is a senior role, we believe that unique talents and perspectives can surpass traditional experience metrics. We seek an individual who can make an immediate impact from day one and contribute to our team’s learning journey.Your RoleAs an Applied AI Engineer, you will operate at the crossroads of product development, engineering, and research. You will work hand-in-hand with skilled engineers and end users to create innovative tools for our internal teams and external clientele. Your contributions will help shape technical solutions, guide strategic initiatives, and enrich our company culture.Key Responsibilities:Collaborate with product and engineering teams to gain insights into customer challengesResearch and implement real-world applications of advanced AI modelsDesign and execute impactful solutions for both internal tools and customer-facing productsInfluence engineering practices, guide product development, and foster a collaborative cultureWhat Motivates You:A passion for curiosity, creativity, and quick adaptationCreating full-stack applications that bring AI to lifeKeeping abreast of the latest trends in AI and LLM prompting techniquesChallenging the limits of what is achievable with AI agentsThriving in fast-paced, collaborative environments

About WorkOS WorkOS is revolutionizing the developer landscape by creating cutting-edge tools and APIs that empower businesses to achieve Enterprise Ready status. Our platform is the backbone for authentication, identity management, authorization, and other essential infrastructures, enabling developers to securely scale their products for large enterprises.Having recently secured a $100M Series C funding round, valuing the company at $2B, we are supported by leading investors such as Meritech, Sapphire, Greenoaks, Craft, Abstract, and Audacious. WorkOS is proud to serve many of the fastest-growing AI companies, including OpenAI, Cursor, Perplexity, Vercel, and Plaid.As AI technology evolves, WorkOS stands at the forefront of Human and Agent Authentication, Identity, and Access Control, helping businesses navigate crucial questions about agent identity and permissions. Our rapidly expanding customer base features hundreds of innovative software companies developing the next generation of enterprise-ready solutions.About the RoleWe are assembling an Applied AI team dedicated to significantly enhancing productivity across Engineering, Sales, Support, and Operations while also developing AI functionalities for our clients.As an Applied AI Engineer, you will design and deploy transformative AI systems that redefine how WorkOS develops, markets, and supports its software. You will focus on creating robust tools and workflows that are essential for daily operations, while also exploring novel AI capabilities for our users.Join a small, high-ownership team that:Identifies challenges based on measurable impact.Rapidly transitions from idea to prototype to production in days or weeks.Quickly adapts to evolving models, tools, and best practices.This role offers substantial visibility across the organization.What You’ll DoCollaborate closely with Engineering, Sales, Support, and Operations to identify high-impact internal challenges where AI can enhance efficiency or facilitate new workflows.Design and construct tools that integrate seamlessly into daily operations—agents, automations, and workflows that are reliable, observable, and easy to maintain.Leverage LLMs, embeddings, retrieval systems, and tool-calling to connect with documents, Slack, GitHub, CRM systems, analytics, support frameworks, and internal services.Transform repetitive, multi-step manual tasks into streamlined, AI-driven processes that span various applications and data sources.Stay informed about emerging models and tools, conduct focused experiments, and assist the team in continuous improvement.

About Us:At LangChain, we strive to revolutionize the accessibility of intelligent agents. Our goal is to provide a robust framework for agent engineering that empowers developers to transition from initial prototypes to production-ready AI agents that can be trusted by teams. What started as a suite of widely embraced open-source tools has evolved into a comprehensive platform designed for the building, assessment, deployment, and management of agents at scale.Currently, our tools, including LangChain, LangGraph, LangSmith, and Agent Builder, are utilized by various teams delivering tangible AI solutions across both startups and large corporations. Millions of developers depend on LangChain to empower AI initiatives at prestigious companies like Replit, Clay, Coinbase, Workday, Lyft, Cloudflare, Harvey, Rippling, Vanta, and 35% of the Fortune 500.With $125M raised in our Series B round from IVP, Sequoia, Benchmark, CapitalG, and Sapphire Ventures, we are in a phase of rapid growth, continuously innovating new products while ensuring every team member has a significant impact on our development and collaborative processes. LangChain is a place where your contributions can influence the real-world application of this transformative technology.About the Role:We are seeking talented Applied AI Engineers to assist in creating AI agents that enhance various aspects of LangChain, from Marketing and Go-To-Market strategies to Recruiting, Support, Internal Tools, and our Core Product.In this position, you will take ownership of specific problem areas, collaborating closely with relevant teams to design, construct, and deploy production-grade agents, workflows, and applications that revolutionize our operational processes. Your contributions will directly support LangChain’s vision of making intelligent, autonomous software a reality for both our internal teams and our clients. Some projects may be open source, contributing to the LangChain and LangGraph ecosystems while establishing new benchmarks for AI development practices.If you are a full-stack software engineer eager to implement AI agents in practical use cases and witness their impact on business outcomes, we invite you to apply.

Join Our Team as an Applied AI EngineerAt Rowspace, we're at the forefront of AI research and engineering, and we are looking for an Applied AI Engineer to help revolutionize how our platform uncovers vital financial insights. Your week may involve developing and deploying AI agents based on client feedback, creating evaluation frameworks for AI performance, and designing sophisticated retrieval systems to optimize AI within financial workflows.Your ResponsibilitiesIntegrate groundbreaking AI research to develop systems that comprehend financial contexts and business concepts.Construct retrieval pipelines that intelligently extract and synthesize insights from unstructured data sources such as PDFs, emails, and presentations.Develop workflows that empower AI systems to analyze financial relationships, conduct benchmarking, and perform comparative analyses.Design and maintain knowledge graphs that represent intricate financial relationships, entity connections, and market dynamics.Create evaluation frameworks to assess and enhance AI performance in investment research, due diligence, and portfolio monitoring.Implement systems ensuring traceability from AI outputs to primary data sources.Experiment with innovative LLM orchestration patterns and context management techniques tailored for financial applications.Guide the technical direction and establish best practices for AI application development at Rowspace.Engage in rapid iteration with direct customer feedback to continuously enhance AI systems based on real-world usage.Oversee the deployment and operation of production systems end-to-end, ensuring reliability, performance, and maintainability across the technology stack.

About Komodo Health We Bring Data to Life Komodo Health’s mission is to alleviate the global burden of disease. The company’s Healthcare Map integrates de-identified patient data with advanced algorithms and clinical expertise, creating a detailed view of the U.S. healthcare system. This foundation supports a suite of software applications that help partners address complex healthcare challenges, monitor patient behaviors, spot treatment trends, and identify care gaps. Komodo Health values excellence, growth, results, and enjoying the journey. The team brings together professionals from varied backgrounds who share a commitment to improving health outcomes. Role Overview: Applied AI Engineer Healthcare in the U.S. is intricate, and Komodo Health tackles these challenges through data-driven solutions. By mapping the patient journey nationwide, the company helps pharmaceutical firms, payers, and healthcare systems make decisions that improve patient care. Labs@Komodo builds AI-native platforms and systems that turn data into actionable insights. The team developed Marmot, Komodo’s AI-native product, which embeds AI into both the user interface and development workflow. By combining Komodo’s healthcare data with modern large language models (LLMs), Marmot delivers real-world insights for healthcare stakeholders. What You Will Do Design and implement end-to-end AI solutions for real products and internal tools. Work at the intersection of applied research, engineering, and product development. Integrate modern AI techniques into scalable, production-ready systems. Collaborate with product, platform, and data teams to build AI capabilities that advance healthcare data use. Location San Francisco, CA

About the Role sfcompute is hiring an Applied AI Engineer in San Francisco, CA. This position focuses on building and deploying AI models that support real business needs. The work involves using advanced technologies to create practical solutions that improve how teams operate. What You Will Do Develop and implement AI models tailored to business goals Work closely with teams across the company to understand their challenges Deliver solutions that boost productivity and efficiency

ABOUT USAt Applied Compute, we are pioneers in developing Specific Intelligence for enterprises, creating agents that learn continuously from a company’s processes, data, expertise, and objectives. Our mission is to establish a continual learning platform that captures context, memory, and decision traces throughout the organization, enabling specialized agents to perform meaningful tasks.Why Join Us: Our team operates at a unique intersection of innovation. Our product team is responsible for crafting a platform that serves as the backbone for a new generation of digital coworkers. Meanwhile, our research team explores the cutting edge of post-training and reinforcement learning to enhance product experiences. Our applied research engineers collaborate closely with clients to deploy agents effectively in real-world scenarios. This synergy of robust product development, extensive research, and direct client engagement is essential for us to revolutionize AI in the enterprise landscape.Our Team: Comprising engineers, researchers, and operations experts, our team includes many former founders with extensive experience. We have developed RL infrastructure at OpenAI, data foundations at Scale AI, and other systems at companies like Two Sigma and Watershed. We proudly serve Fortune 50 clients and are supported by top-tier investors including Kleiner Perkins, Benchmark, Sequoia, Lux, and Greenoaks.Who Thrives Here: We seek individuals passionate about utilizing cutting-edge research and complex systems to address real-world challenges. Comfort navigating diverse environments, whether it’s a new codebase, unfamiliar customer data architecture, or unexplored problem domains, is essential. Our team values genuine client engagement — listening, empathizing, and understanding the realities of work in their organizations. Those with entrepreneurial spirits, rich project experiences, or proven capabilities to manage tasks end-to-end will excel in our environment.THE POSITIONAs a Software Engineer, you will be instrumental in building the products and interfaces utilized by customers and internal teams. You will manage the entire application platform stack, from collaborative human-AI workspace systems to backend workflows orchestrating sandboxed agent sessions, and the continual learning SDK that provides engineers with oversight of the agent development lifecycle.

ABOUT THE ROLE:As an AI Engineer at Varick, you will take charge of designing and optimizing the intelligence layer within our enterprise operations. This involves creating agent systems that efficiently handle thousands of transactions, make classification decisions, and learn from human interactions.This position is suited for engineers with extensive experience in LLMs, agent architectures, and evaluation systems. You have successfully developed agent workflows that operate in production, not merely in demo environments. Your expertise includes prompt engineering, retrieval, tool calling, multi-agent orchestration, and the evaluation frameworks necessary for deploying trustworthy AI systems in enterprise settings.WHAT YOU'LL DO:• Design and implement agent architectures that tackle complex enterprise workflows, focusing on multi-step reasoning, tool calling, and exception handling.• Develop and sustain evaluation systems that ensure agent quality, accuracy, safety, and groundedness.• Create robust prompt systems, retrieval pipelines, and context engineering strategies to ensure reliable agent performance.• Establish feedback loops that empower agents to learn from human corrections and enhance their functionality over time.• Optimize inference costs and latency for production workloads to ensure efficiency.• Define and uphold best practices for agent reliability, observability, and governance.• Stay updated with the latest models, frameworks, and research to ensure impactful deployments into production.WHAT WE'RE LOOKING FOR:• At least 3 years of software engineering experience, with a minimum of 1–2 years dedicated to LLM applications or AI systems in a production environment.• Practical experience in constructing agent workflows featuring tool calling, retrieval, and multi-step reasoning.• A profound understanding of prompt engineering, context engineering, and methods to elicit reliable behavior from LLMs.• Experience in developing evaluation systems to assess AI output quality.• Proficient in Python with a solid foundation in backend engineering principles.• You have delivered AI features to actual users and have navigated challenges such as hallucinations, edge cases, accuracy drops, and cost management.• Must be based in San Francisco.

Join Our Mission at Abby CareAt Abby Care, we are dedicated to transforming the landscape of family caregiving, addressing one of the most significant challenges of our time. Our goal is to empower over 50 million unpaid family caregivers across the United States by providing them with the training and support they need to get compensated for the invaluable care they provide at home.We are developing a cutting-edge, tech-driven family-first care platform designed to enhance care delivery, improve health outcomes, and ensure a superior experience for families nationwide. As we expand our impact, we are seeking passionate individuals to join our team. With partnerships alongside leading insurance providers, healthcare organizations, and community groups, we are backed by top-tier, mission-driven venture capitalists who share our vision of supporting families throughout the country.Our team comprises high-caliber professionals with backgrounds at renowned companies such as Uber, Scale AI, DoorDash, Dropbox, and Meta. Together, we are reimagining family caregiving.Your Role as an Applied AI EngineerWe are on the lookout for a skilled and motivated Applied AI Engineer to join our dynamic team. Reporting to the VP, Head of Engineering, this full-time position is based in San Francisco, CA, with an in-person presence required four days a week.In this role, you will play a crucial part in designing and building AI-driven products that serve as intelligent copilots for families and healthcare providers. You will create AI systems that facilitate family caregiving, enhance clinician support in care delivery, and explore innovative home-based care models. Your work will involve hands-on engagement with AI models and real-world clinical and operational data, contributing to the evolution of AI-assisted caregiving and shaping the future of care as a key early engineer.