Senior Data Engineer

About the role

Design, build and operate data infrastructure for a clinical trial design platform; pipelines from PDF extraction to Aurora and GraphDB serving LangGraph agentic AI workflows.

Requirements

• Strong Python incl. PDF parsing
• Advanced PostgreSQL/Aurora SQL
• Graph databases
• AWS pipeline services
• FastAPI
• RAG pipelines for LangChain/LangGraph
• Workflow orchestration (Airflow etc.)
• Terraform/CDK, Docker, Git

What you'll do

• Build ingestion pipelines for clinical trial documents
• Design data models in Aurora and GraphDB
• Build embedding/vectorization pipelines
• Data quality validation and lineage

Where this was posted

• workable

  last seen 2h ago
  View on workable