AI Engineer
Bristol Myers Squibb
15 days ago
Remote friendly (Boston, MA)
United States
IT
Summary
AI Engineer (AI Venture Studio delivery team) partnering with engineers and stakeholders to build data pipelines, integrations, and agentic AI systems for AI Accelerator projects.
Responsibilities
- Design, build, and maintain ETL workflows and data transformations; integrate internal/external APIs and data sources.
- Develop/manage PostgreSQL/RDS, vector databases (OpenSearch, Milvus, S3 Vectors), and knowledge graphs (Amazon Neptune, Neo4j).
- Build/operate AWS data infrastructure using S3, Athena, RDS, ElastiCache (Redis), and Fargate.
- Build multi-agent systems with LangGraph (state management, fan-out/fan-in orchestration, subgraphs).
- Create tool integrations and MCP servers using FastMCP.
- Implement LLM workflows using OpenAI/Anthropic/Gemini via AWS Bedrock and APIs.
- Build evaluation/observability pipelines (LangSmith or promptfoo).
- Write automated tests (unit/integration/e2e) with pytest; support TDD and CI test automation.
- Collaborate with AI Engineers, Pod Leads, and Research scientists; participate in code reviews/design discussions.
Qualifications & Skills
- BS+ in CS/Engineering/Data Science/scientific field.
- 1–3 years in data/software/computational roles.
- Python (Pandas, NumPy) and FastAPI; GitHub and DevOps.
- AWS pipelines (S3, RDS, Athena, ElastiCache, Fargate) and PostgreSQL/vector DB/knowledge graph experience.
- LLM app development (prompting, tool use, structured outputs); familiarity with LangGraph/LangChain/PydanticAI.
- Experience writing LLM evaluations and data quality checks.
- Agile experience; ability to adapt quickly.
Benefits (explicitly listed)
- Medical, pharmacy, dental, vision; wellbeing support; 401(k) and insurance/disability coverage; Paid Time Off.
Application instructions
- If you’re intrigued but not a perfect match, apply anyway.
AI Engineer (AI Venture Studio delivery team) partnering with engineers and stakeholders to build data pipelines, integrations, and agentic AI systems for AI Accelerator projects.
Responsibilities
- Design, build, and maintain ETL workflows and data transformations; integrate internal/external APIs and data sources.
- Develop/manage PostgreSQL/RDS, vector databases (OpenSearch, Milvus, S3 Vectors), and knowledge graphs (Amazon Neptune, Neo4j).
- Build/operate AWS data infrastructure using S3, Athena, RDS, ElastiCache (Redis), and Fargate.
- Build multi-agent systems with LangGraph (state management, fan-out/fan-in orchestration, subgraphs).
- Create tool integrations and MCP servers using FastMCP.
- Implement LLM workflows using OpenAI/Anthropic/Gemini via AWS Bedrock and APIs.
- Build evaluation/observability pipelines (LangSmith or promptfoo).
- Write automated tests (unit/integration/e2e) with pytest; support TDD and CI test automation.
- Collaborate with AI Engineers, Pod Leads, and Research scientists; participate in code reviews/design discussions.
Qualifications & Skills
- BS+ in CS/Engineering/Data Science/scientific field.
- 1–3 years in data/software/computational roles.
- Python (Pandas, NumPy) and FastAPI; GitHub and DevOps.
- AWS pipelines (S3, RDS, Athena, ElastiCache, Fargate) and PostgreSQL/vector DB/knowledge graph experience.
- LLM app development (prompting, tool use, structured outputs); familiarity with LangGraph/LangChain/PydanticAI.
- Experience writing LLM evaluations and data quality checks.
- Agile experience; ability to adapt quickly.
Benefits (explicitly listed)
- Medical, pharmacy, dental, vision; wellbeing support; 401(k) and insurance/disability coverage; Paid Time Off.
Application instructions
- If you’re intrigued but not a perfect match, apply anyway.