About the job
About Contextual AI
At Contextual AI, we are pioneering a transformation in the way AI Agents operate by tackling the most pressing challenge in AI: context. By providing the right context at the right moment, we enable enterprises to achieve the precision and scalability they need from AI. Our robust enterprise AI development platform bridges the gap between cutting-edge AI research and the practical needs of developers. Our comprehensive platform simplifies the process for AI developers to seamlessly ingest and query documents from enterprise data sources, integrating retrieval outcomes into their business workflows effortlessly.
Founded by the trailblazers of Retrieval-Augmented Generation (RAG), the foundational technology that links foundational models to timely and relevant data, Contextual AI is backed by some of the most innovative venture capitalists in the industry. We are not merely a part of the enterprise AI revolution; we are at its forefront. Join us in creating a future where AI transcends mere question answering to genuinely transform businesses.
Job Overview
The Data Platform team within Contextual AI is integral to powering product development, applied research, and managing data-heavy workloads for our customers. This is a unique opportunity to influence the technical vision of the data engineering team, contributing to groundbreaking projects within a greenfield environment.
What You’ll Do:
- Design and develop scalable services, APIs, and databases to efficiently handle the daily processing and ingestion of petabytes of data.
- Enhance state-of-the-art multimodal LLMs to maximize document understanding capabilities.
- Create and implement thorough evaluation pipelines for end-to-end agentic RAG workflows.
- Architect and construct streaming infrastructure and data orchestration systems, including vector databases.
- Collaborate with machine learning researchers to interpret state-of-the-art requirements for RAG systems, translating them into actionable service specifications.
- Engage directly with product managers and application engineers to gather customer requirements for end-to-end RAG systems, and convert these into viable technical solutions.
- Ensure seamless integration with machine learning models and pipelines, facilitating effective model deployment and management.
- Provide mentorship and guidance to junior team members, fostering a culture of knowledge sharing and professional development.
What We’re Seeking:
- Education: A Bachelor’s degree in Computer Science, Software Engineering, or a related field.
- Experience: Minimum of 2 years of relevant experience in data engineering or a related field.
- Strong understanding of scalable data architectures and design principles.
- Proficiency in modern programming languages and frameworks.
- Experience with machine learning principles and practices is a plus.

