AI & Data Engineer, Data Discovery Services
Core
Building production data pipelines and semantic knowledge layers to make enterprise data findable and actionable for AI systems and LLMs.
Role type
Senior hands-on IC AI & Data Engineer
Builds
Production data pipelines, metadata enrichment flows, search indexes, and semantic knowledge layers for enterprise data discovery
Domain
Life Sciences / Enterprise Data Platforms / Applied AI
Deliverable
production ML models | product features
Required skills
Python, SQL, Databricks, AWS Glue, ETL/ELT patterns, data modeling, pipeline orchestration, OpenSearch/Elasticsearch, metadata management
Preferred skills
Semantic knowledge layers, RAG patterns, vector search, embeddings, AI agent patterns, MCP, ontology/taxonomy technologies, graph databases
Technologies
Databricks, AWS (S3, Lambda, API Gateway, Glue), OpenSearch, Elasticsearch, Docker, ECS, CloudFormation
Responsibilities
Build and maintain Python pipelines for metadata extraction, enrichment, and publishing; Tune and optimize search indexes; Build semantic knowledge layers with vector embeddings for RAG; Maintain ontology and taxonomy integrations; Resolve data pipeline issues and add quality checks; Build API endpoints and MCP servers; Design cross-domain metadata mapping pipelines
Seniority
Senior, hands-on IC
