AI Engineer

Responsibilities

• Design, build, and maintain data pipelines that feed AI Accelerator projects, including ETL workflows, data transformations, and integration with internal and external APIs and data sources.
• Develop and manage relational databases (PostgreSQL/RDS), vector databases (Open Search, Milvus, Amazon S3 Vectors), and knowledge graphs (Amazon Neptune, Neo4j).
• Build and operate data infrastructure on AWS, leveraging services such as S3, Athena, RDS, Elasti Cache (Redis), and Fargate.
• Build and maintain multi-agent systems using Lang Graph, including state management, fan-out/fan-in orchestration, and subgraph composition.
• Develop tool integrations and MCP (Model Context Protocol) servers using FastMCP to enable agent interoperability.
• Implement LLM-powered workflows integrating foundational models (OpenAI, Anthropic, Gemini) via AWS Bedrock and direct API access.
• Build evaluation and observability pipelines using tools such as Lang Smith or promptfoo.
• Write and maintain automated test suites (unit, integration, end-to-end) using pytest to ensure reliability of data pipelines and agent workflows.
• Develop evaluation frameworks for LLM outputs, including reference-based metrics and structured output validation.
• Implement data quality checks and validation at system boundaries to catch issues early in the pipeline.
• Support test-driven development practices and contribute to CI test automation.
• Partner with AI Engineers, Pod Leads, and Research scientists to deliver AI Accelerator projects within 12-week cycles.
• Participate in code reviews, design discussions, and technical problem-solving with pod teams.

• Bachelor’s or higher degree in Computer Science, Engineering, Data Science, or a scientific field.
• 1-3 years of experience in data engineering, software engineering, or related technology or computational roles.
• Strong proficiency in Python, including data libraries (Pandas, Num Py) and web frameworks (FastAPI).
• Experience with data pipelines on AWS (S3, RDS, Athena, Elasti Cache, Fargate) and relational databases (PostgreSQL), vector databases, or knowledge graphs.
• Experience with LLM application development, including prompt engineering, tool use, and structured outputs.
• Familiarity with agent frameworks (Lang Graph, Lang Chain, PydanticAI) or demonstrated ability to learn new frameworks quickly.
• Comfort with Git Hub and Dev Ops practices.
• Effective use of coding agents (e.g., Claude Code, Codex, Gemini CLI).
• Knowledge of and experience in agile ways of working.
• Experience writing automated tests (unit, integration, end-to-end) using pytest or similar frameworks.
• Curious and inquisitive mindset with the ability to adapt quickly to changing priorities.