AI Engineer
Bristol Myers Squibb
5 hours ago
Remote friendly (Madison, NJ)
United States
IT
Summary
As an AI Engineer (AI Venture Studio delivery team), you will build data pipelines, integrations, and agentic AI systems that power AI Accelerator projects.
Key Responsibilities
- Design, build, and maintain data pipelines (ETL, transformations, internal/external API integrations).
- Develop and manage relational databases (PostgreSQL/RDS), vector databases (OpenSearch, Milvus, S3 Vectors), and knowledge graphs (Amazon Neptune, Neo4j).
- Build and operate AWS data infrastructure (S3, Athena, RDS, ElastiCache/Redis, Fargate).
- Build multi-agent systems with LangGraph (state management, fan-out/fan-in orchestration, subgraph composition).
- Develop tool integrations and MCP servers using FastMCP; implement LLM workflows via AWS Bedrock and APIs.
- Build evaluation/observability pipelines (LangSmith or promptfoo).
- Write automated tests (unit/integration/e2e) with pytest; develop LLM evaluation frameworks and data quality checks.
- Partner with AI Engineers, Pod Leads, and Research scientists; contribute to code reviews and design discussions.
Qualifications / Required Skills
- BS+ in CS/Engineering/Data Science or scientific field.
- 1–3 years in data/software/computational roles.
- Python (Pandas/NumPy) and FastAPI.
- AWS pipelines (S3, RDS, Athena, ElastiCache, Fargate) and experience with PostgreSQL/vector DBs/knowledge graphs.
- LLM app development (prompting, tool use, structured outputs) and agent frameworks (LangGraph/LangChain/PydanticAI) or ability to learn quickly.
- GitHub/DevOps; automated testing with pytest.
- Agile experience; curious/adaptable.
Benefits (examples)
- Health coverage; wellbeing support; 401(k) and insurance/disability benefits.
- Paid time off (flexible time off or annual vacation depending on role/location).
Application Instructions
- If the role doesn’t perfectly match your resume, apply anyway.
As an AI Engineer (AI Venture Studio delivery team), you will build data pipelines, integrations, and agentic AI systems that power AI Accelerator projects.
Key Responsibilities
- Design, build, and maintain data pipelines (ETL, transformations, internal/external API integrations).
- Develop and manage relational databases (PostgreSQL/RDS), vector databases (OpenSearch, Milvus, S3 Vectors), and knowledge graphs (Amazon Neptune, Neo4j).
- Build and operate AWS data infrastructure (S3, Athena, RDS, ElastiCache/Redis, Fargate).
- Build multi-agent systems with LangGraph (state management, fan-out/fan-in orchestration, subgraph composition).
- Develop tool integrations and MCP servers using FastMCP; implement LLM workflows via AWS Bedrock and APIs.
- Build evaluation/observability pipelines (LangSmith or promptfoo).
- Write automated tests (unit/integration/e2e) with pytest; develop LLM evaluation frameworks and data quality checks.
- Partner with AI Engineers, Pod Leads, and Research scientists; contribute to code reviews and design discussions.
Qualifications / Required Skills
- BS+ in CS/Engineering/Data Science or scientific field.
- 1–3 years in data/software/computational roles.
- Python (Pandas/NumPy) and FastAPI.
- AWS pipelines (S3, RDS, Athena, ElastiCache, Fargate) and experience with PostgreSQL/vector DBs/knowledge graphs.
- LLM app development (prompting, tool use, structured outputs) and agent frameworks (LangGraph/LangChain/PydanticAI) or ability to learn quickly.
- GitHub/DevOps; automated testing with pytest.
- Agile experience; curious/adaptable.
Benefits (examples)
- Health coverage; wellbeing support; 401(k) and insurance/disability benefits.
- Paid time off (flexible time off or annual vacation depending on role/location).
Application Instructions
- If the role doesn’t perfectly match your resume, apply anyway.