Principal Engineer, AI Inference Reliability

Cerebras Systems is at the forefront of AI innovation, manufacturing the largest AI chip in the world, which is 56 times bigger than conventional GPUs. Our cutting-edge wafer-scale architecture provides the computational power equivalent to dozens of GPUs on a single chip, simplifying programming to the level of a single device. This pioneering approach enab…

Cerebras Systems is at the forefront of AI technology, developing the world's largest AI chip that is 56 times greater than conventional GPUs. Our innovative wafer-scale architecture delivers the computational capabilities of numerous GPUs on a single chip, simplifying programming to the level of a single device. This groundbreaking approach enables Cerebras to achieve unmatched training and inference speeds, allowing machine learning practitioners to seamlessly execute large-scale ML applications without the complexities of managing extensive GPU or TPU resources. Our clientele includes leading model laboratories, global corporations, and pioneering AI-centric startups. Notably, OpenAI has recently entered into a multi-year partnership with Cerebras, aiming to deploy 750 megawatts of capacity, revolutionizing key workloads with exceptionally rapid inference speeds. Thanks to our extraordinary wafer-scale architecture, Cerebras Inference provides the swiftest Generative AI inference solution available today, operating over ten times faster than GPU-based hyperscale cloud inference services. This significant boost in speed is reshaping the user experience in AI applications, facilitating real-time iterations and enhancing intelligence through advanced agentic computation. About The Role We are looking for an exceptionally talented Deployment Engineer to design and manage our state-of-the-art inference clusters. In this role, you will have the opportunity to work with the unparalleled Wafer-Scale Engine (WSE) and the systems that exploit its extraordinary capabilities.

Cerebras Systems is revolutionizing the AI landscape with the world's largest AI chip, which is 56 times more extensive than traditional GPUs. Our innovative wafer-scale architecture enables us to deliver the computational power of dozens of GPUs on a single chip, while offering the ease of programming like a single device. This groundbreaking approach empowers Cerebras to achieve unparalleled training and inference speeds, allowing machine learning practitioners to run large-scale ML applications effortlessly without the complexities of managing numerous GPUs or TPUs.Cerebras serves a diverse clientele that includes leading model laboratories, global corporations, and pioneering AI-focused startups. Recently, OpenAI announced a multi-year collaboration with Cerebras to harness 750 megawatts of scale, significantly enhancing key workloads through ultra-fast inference capabilities.With our cutting-edge wafer-scale architecture, Cerebras Inference provides the fastest Generative AI inference solution globally, exceeding the speed of GPU-based hyperscale cloud inference services by over ten times. This extraordinary speed transformation is reshaping the user experience of AI applications, facilitating real-time iterations and boosting intelligence through enhanced agentic computation.

At Cerebras Systems, we are revolutionizing AI computing by developing the world’s largest AI chip, which is 56 times larger than traditional GPUs. Our innovative wafer-scale architecture provides the computational power equivalent to dozens of GPUs on a single chip, simplifying programming to the level of a single device. This unique approach enables us to achieve unparalleled training and inference speeds, allowing machine learning practitioners to run large-scale ML applications without the complexity of managing multiple GPUs or TPUs.Our esteemed clientele includes leading model laboratories, prominent global enterprises, and forward-thinking AI-native startups. Notably, OpenAI has entered a multi-year partnership with Cerebras to leverage 750 megawatts of scale, enhancing critical workloads with ultra-high-speed inference.With our groundbreaking wafer-scale architecture, Cerebras Inference delivers the fastest Generative AI inference solution globally, outperforming GPU-based hyperscale cloud inference services by over tenfold. This dramatic increase in speed is transforming how users experience AI applications, facilitating real-time iterations and enhancing intelligence through additional agentic computation.Location: Toronto / SunnyvaleWe are seeking a highly technical, hands-on engineering leader for our Inference Service Platform. In this role, you will guide a high-performing team to address a critical challenge: scaling large language model (LLM) inference on Cerebras’ advanced compute clusters and delivering a world-class, on-premise solution for enterprise customers. You will establish the technical vision while maintaining close engagement with the code, focusing on architecting highly reliable and low-latency distributed systems. If you possess proven expertise in distributed systems and scaling modern model-serving frameworks, we encourage you to apply.

Cerebras Systems is at the forefront of AI innovation, creating the world’s largest AI chip, which is 56 times larger than traditional GPUs. Our groundbreaking wafer-scale architecture delivers the computational power equivalent to dozens of GPUs on a single chip, combined with the programming simplicity of a unified device. This innovative approach allows us to offer unparalleled training and inference speeds, enabling machine learning practitioners to execute extensive ML applications seamlessly, without the complexities of managing multiple GPUs or TPUs.Cerebras boasts an impressive clientele, including premier model labs, global corporations, and pioneering AI startups. Recently, OpenAI announced a multi-year partnership with Cerebras, aimed at deploying 750 megawatts of scale, revolutionizing critical workloads with ultra-fast inference capabilities.Our unique wafer-scale architecture enables Cerebras Inference to provide the fastest Generative AI inference solution globally, surpassing GPU-based hyperscale cloud inference services by more than tenfold. This remarkable enhancement in speed is reshaping the AI application user experience, facilitating real-time iteration and boosting intelligence through enhanced computational capabilities.About The RoleThe Inference ML Engineering team at Cerebras Systems is committed to empowering our rapid generative inference solution through intuitive APIs, supported by a distributed runtime that operates on extensive clusters of our proprietary hardware. Our goal is to enable enterprises, developers, and researchers to fully harness the capabilities of our platform, leveraging its exceptional performance, scalability, and flexibility. The team collaborates closely with cross-functional groups, including compiler developers, cluster orchestrators, ML scientists, cloud architects, and product teams, to deliver impactful solutions that redefine the limits of ML performance and usability.As a Senior Software Engineer on the Inference ML Engineering team, you will be instrumental in designing and implementing APIs, ML features, and tools that facilitate the execution of state-of-the-art generative AI models on our custom hardware. Your role will involve architecting solutions that allow for seamless model translation and execution, ensuring high throughput and minimal latency while maintaining user-friendliness. You will lead technical initiatives and collaborate with other engineering teams to enhance our solutions.

Role Overview Cerebras Systems is looking for a Staff Software Engineer focused on Inference Cloud. This position is based in Sunnyvale, CA. What You Will Do Design, develop, and optimize software for inference products Work closely with team members to improve performance and reliability Apply advanced AI and machine learning methods to real-world challenges Collaboration Work alongside experienced engineers on projects that shape the future of inference technology at Cerebras Systems.

Cerebras Systems is at the forefront of AI technology, developing the world’s largest AI chip that is 56 times larger than conventional GPUs. Our innovative wafer-scale architecture delivers the computational power of dozens of GPUs within a single chip, simplifying programming and enhancing performance. This unique capability enables Cerebras to provide unparalleled training and inference speeds, allowing machine learning practitioners to execute large-scale ML applications seamlessly without the complexities of managing extensive GPU or TPU infrastructures.Cerebras serves a diverse clientele, including top-tier model labs, global enterprises, and pioneering AI-native startups. OpenAI has recently partnered with Cerebras to leverage 750 megawatts of power, significantly enhancing key workloads through ultra high-speed inference.Our cutting-edge wafer-scale architecture has made Cerebras Inference the fastest Generative AI inference solution globally, achieving speeds over ten times faster than GPU-based hyperscale cloud inference services. This revolutionary speed is transforming the user experience of AI applications, facilitating real-time iteration and boosting intelligence through enhanced computational capabilities.About The RoleWe invite you to join Cerebras as a Performance & Reliability Engineer within our dynamic Co-Design and Next Generation Team. Our groundbreaking CS-3 system has established benchmarks for high-performance ML training and inference solutions, utilizing a chip the size of a dinner plate with 44GB of on-chip memory that exceeds traditional hardware capabilities. In this role, you will focus on characterizing and optimizing the performance and reliability of state-of-the-art AI models operating on Cerebras' revolutionary hardware.ResponsibilitiesCharacterize and enhance the performance and reliability of advanced ML hardware/software systems, focusing on minimizing power and thermal fluctuations.Analyze ML workloads, software kernels, and hardware architecture for their power and performance impacts, synthesizing high-level insights across these layers.Develop innovative software solutions to enhance system performance and efficiency.

Join Apptronik, a leading human-centered robotics company revolutionizing the world with AI-powered robots designed to enhance every aspect of life. Our flagship humanoid robot, Apollo, is engineered for seamless collaboration with people, initially focusing on critical sectors like manufacturing and logistics, and poised for future applications in healthcare, domestic environments, and more.We are at the forefront of embodied AI, utilizing our extensive expertise across the entire robotics stack to address some of society's most pressing challenges. As part of our team, you will play a pivotal role in scaling Apollo for market readiness, navigating complex issues around safety, commercialization, and mass production to make a positive impact on the world.JOB SUMMARYWe are in search of a Principal Engineer to spearhead the development of high-performance embedded AI systems and advanced simulation infrastructure for our humanoid robots. This position emphasizes GPU-centric workload orchestration, graphics-driven simulation performance, and robust on-device AI execution.The ideal candidate will possess extensive experience in graphics, display systems, Linux platforms, and low-level embedded software, enabling them to enhance simulation fidelity and optimize real-time AI workloads across robotic platforms.ESSENTIAL DUTIES AND RESPONSIBILITIESGPU Workload OrchestrationArchitect and implement a pipeline for the effective utilization of GPUs across various concurrent AI workloads.Design and develop schedulers and runtime systems to coordinate perception, planning, and control models on-device.Optimize latency, throughput, and power efficiency for real-time robotic operations.On-Device AI SystemsEnhance the robustness and reliability of deployed AI models in constrained embedded environments.Facilitate efficient execution of multi-model pipelines (vision, tracking, control).Collaborate with ML teams to co-design models and runtime systems effectively.Simulation PerformanceLead initiatives to significantly boost simulation throughput and realism.Optimize rendering, physics integration, and data pipelines through graphics expertise.Align simulation outputs with the requirements of real-world deployments.Embedded Systems & Platform IntegrationOversee low-level system integration across Linux-based platforms.Collaborate across kernel, drivers, HAL, and user-space layers to ensure seamless operation.

Join our dynamic team as a Senior Site Reliability Engineer focused on AI/ML solutions. In this role, you will leverage your expertise to enhance the reliability, scalability, and performance of our cutting-edge AI-driven products. You will work collaboratively with cross-functional teams to design, implement, and maintain robust systems that support our mission to revolutionize surgical technology.

Join CoreWeave as a Senior Software Engineer I specializing in inference, where you will spearhead architectural designs, elevate engineering standards, and significantly enhance latency, throughput, and reliability across various services. Collaborate closely with product, orchestration, and hardware teams to advance our Kubernetes-native inference platform, ensuring we achieve stringent P99 SLAs at scale.

Cerebras Systems is at the forefront of AI technology, having developed the world's largest AI chip, which is 56 times larger than traditional GPUs. Our innovative wafer-scale architecture delivers the AI computing power equivalent to dozens of GPUs on a single chip, simplifying programming to a single device. This revolutionary design enables Cerebras to provide unmatched training and inference speeds, empowering machine learning practitioners to seamlessly execute large-scale ML applications without the complexities of managing multiple GPUs or TPUs.Our clientele includes elite model labs, global corporations, and pioneering AI-native startups. Notably, OpenAI recently entered into a multi-year partnership with Cerebras to deploy 750 megawatts of scale, significantly enhancing key workloads with ultra high-speed inference.Thanks to our groundbreaking wafer-scale architecture, Cerebras Inference offers the fastest Generative AI inference solution globally, achieving speeds over 10 times faster than GPU-based hyperscale cloud inference services. This substantial speed boost is transforming user experiences in AI applications by enabling real-time iterations and enhancing intelligence through additional agentic computation.The RoleWe are seeking a highly technical and hands-on Engineering Manager to lead our on-field Kernel Reliability team. You will guide a high-performing team in addressing a critical challenge: enhancing the reliability of our advanced compute clusters along with the associated inference, training, and internal production services. In this influential role, you will define the technical vision while remaining closely engaged with the code, crafting scalable solutions for our rapidly expanding system production and software service offerings. If you possess proven expertise in software or hardware reliability, diagnostic tool development, or failure analysis and debugging, we invite you to connect with us.ResponsibilitiesProvide hands-on technical leadership, owning the technical vision and roadmap for kernel-centric reliability concerning both internal and customer-facing systems.

Cerebras Systems is revolutionizing the AI landscape with the world's largest AI chip, which is 56 times larger than traditional GPUs. Our innovative wafer-scale architecture delivers the computational power of multiple GPUs on a single chip, simplifying programming and enabling unparalleled training and inference speeds. This technology allows our users to run extensive machine learning applications seamlessly, eliminating the complexities associated with managing numerous GPUs or TPUs.Our clientele includes leading model labs, global corporations, and pioneering AI startups. Recently, OpenAI announced a multi-year collaboration with Cerebras, aiming to deploy 750 megawatts of power, significantly enhancing their workloads with ultra-fast inference capabilities.With our groundbreaking wafer-scale architecture, Cerebras Inference provides the fastest Generative AI inference solution globally, outperforming GPU-based hyperscale cloud services by over tenfold. This remarkable speed enhancement is transforming user experiences in AI applications, facilitating real-time iterations and amplifying intelligence through advanced computational capabilities.About The RoleWe are in search of a highly technical and hands-on Software Engineer to join our Kernel Reliability team. In this pivotal role, you will address the crucial task of enhancing the reliability of our advanced compute clusters, along with the inference, training, and internal production services. You will work closely with the code to develop solutions that scale alongside our rapidly evolving production systems and software services. If you possess strong foundations in systems, debugging, and failure analysis and have a passion for creating tools and solving complex reliability challenges, we would love to connect with you. New graduates are encouraged to apply.

About the RoleCoreWeave operates some of the largest GPU clusters globally. The AI infrastructure behind these clusters plays a crucial role in determining workload placement, resource sharing, and system reliability under continuous pressure.As a Principal Engineer specializing in AI Infrastructure, you will spearhead the design and enhancement of cluster orchestration systems, including Slurm, Kubernetes, SUNK, and the control planes that facilitate AI training, inference, and model onboarding at scale.Your responsibilities will include defining long-term architecture, addressing complex scaling challenges, and establishing technical direction across various teams. Your contributions will significantly impact the speed at which customers can deploy models, the efficiency of GPU utilization, and the overall reliability of the platform at scale.

Cerebras Systems is at the forefront of AI innovation, creating the world's largest AI chip that is 56 times larger than traditional GPUs. Our unique wafer-scale architecture delivers the computational power of numerous GPUs on a single chip, simplifying programming while providing unparalleled training and inference speeds. This revolutionary approach enables users to run extensive machine learning applications effortlessly, eliminating the complexity of managing multiple GPUs or TPUs.Cerebras serves a diverse clientele, including leading model labs, major global enterprises, and pioneering AI-native startups. Recently, OpenAI announced a multi-year partnership with Cerebras, aiming to deploy 750 megawatts of scale that will redefine key workloads with ultra-high-speed inference.Our groundbreaking wafer-scale architecture ensures that Cerebras Inference provides the fastest Generative AI inference solution globally, achieving speeds that are over ten times faster than GPU-based hyperscale cloud services. This significant enhancement in performance is transforming the user experience of AI applications, facilitating real-time iteration and boosting intelligence through enhanced computational capabilities.About The RoleWe are seeking a Senior Performance Analyst to join our dynamic Product team. As a specialist in state-of-the-art inference performance, you will be the go-to expert on how Cerebras measures up against alternative inference providers in terms of pricing and performance. This role combines performance benchmarking from foundational principles with competitive intelligence. The position revolves around two key pillars:Performance BenchmarkingYou will develop, execute, and sustain reproducible benchmarks that assess Cerebras inference performance for actual customer workloads. This includes metrics such as tokens per second, time to first token, latency under concurrency, and total cost of ownership (TCO).Competitive AnalysisYou will analyze market trends and competitor offerings to position Cerebras effectively within the inference landscape.

As a Fleet Reliability Engineer at Applied Intuition, you will be at the forefront of ensuring the reliability and performance of our advanced fleet systems. Your expertise will play a crucial role in the development and deployment of our cutting-edge technology, optimizing fleet operations to guarantee safety and efficiency.

Illumio’s Senior Site Reliability Engineer role is based at the company’s Sunnyvale, California headquarters. This is an on-site position, requiring presence in the office five days a week. Role overview This position focuses on building and maintaining reliable, scalable infrastructure for Illumio’s applications and services, with an emphasis on Azure cloud solutions. The Senior SRE supports both SaaS and on-premises offerings, working closely with engineering teams to ensure operational resilience and security across hybrid environments. What you will do Design, deploy, and maintain highly available infrastructure on Azure for Illumio’s products. Automate provisioning and configuration management using Infrastructure as Code tools such as Terraform or ARM templates. Develop and manage CI/CD pipelines to improve software delivery and deployment processes. Monitor system and application health using Azure monitoring and logging tools, and optimize for performance and availability. Lead incident response, perform root cause analysis, and document findings to drive continuous improvement. Collaborate with development teams to design scalable, reliable architectures and provide guidance on cloud-native best practices. Engineering at Illumio The engineering team values autonomy, ownership, and collaboration. Work centers on advancing cybersecurity with scalable SaaS services and solutions for on-premises environments. The team emphasizes disciplined engineering, quality, and a supportive culture.

At Coram AI, we are transforming the landscape of video security in the digital age. Our innovative cloud-native platform leverages advanced computer vision and artificial intelligence to empower businesses with enhanced safety, smarter decision-making capabilities, and accelerated operational efficiency through features like real-time alerts, effortless clip sharing, and comprehensive multi-site visibility.Join our dynamic and agile team that prioritizes clarity, craftsmanship, and impactful contributions. Every team member plays a crucial role, delivering significant results and shaping the future of AI-driven security solutions.We are seeking an experienced Engineering Manager to lead our talented AI team at Coram. This team, although small, is exceptionally skilled and operates at the forefront of real-time systems, computer vision, and generative AI.In this hands-on leadership role, you will blend technical guidance, architectural oversight, recruitment, and team management. The ideal candidate will possess up-to-date knowledge of modern deep learning and generative AI, along with substantial experience in building and leading high-performance teams.

Join Cerebras Systems as a Staff Frontend Engineer specializing in Inference. In this pivotal role, you will be instrumental in developing innovative solutions that push the boundaries of AI and machine learning. Your expertise will drive the design and implementation of user-friendly interfaces that enhance our cutting-edge technology.

Join our innovative team at Intuitive Surgical, Inc. as a Principal Research Engineer. In this pivotal role, you will lead advanced research initiatives to enhance our cutting-edge surgical technologies. Your expertise will contribute to the development of innovative solutions that improve patient outcomes and streamline surgical procedures.

At Coram AI, we are revolutionizing video security for the contemporary landscape. Our innovative cloud-native platform leverages advanced computer vision and artificial intelligence to empower businesses to enhance safety, facilitate informed decision-making, and accelerate operations. This includes features such as real-time alerts, effortless clip sharing, and comprehensive visibility across multiple locations.Joining our agile and dynamic team means being part of a collaborative environment that prioritizes clarity, excellence, and impactful contributions. Every team member has a voice, delivers significant work, and plays a crucial role in shaping how AI can foster a safer and more interconnected world.We are seeking engineers who thrive at the nexus of robotics, real-time systems, and deep learning. This position focuses on implementing high-performance vision and multimodal models on robotic platforms, where factors such as latency, reliability, and hardware limitations are paramount.