Senior AI Data Engineer

In this Senior AI Data Engineer role, you will transform semantic models into production-grade knowledge graphs and AI-ready data pipelines. You’ll implement JSON-LD schemas, manage graph databases, and build embedding and vector-search infrastructures to power compliant AI-driven insights. You’ll work closely with ontologists, data engineers, and backend teams to ensure scalable, observable data products. This position is ideal for someone who thrives in greenfield environments shaping the data platform to enable AI across our compliance data.

• Implement JSON-LD semantic models into production systems and build knowledge graph structures reflecting domain models
• Design and manage graph database schemas, queries, and ingestion pipelines with semantic alignment to downstream products
• Develop embedding pipelines and vector infrastructure for semantic search and RAG capabilities
• Operate vector databases and tooling for semantic search and similarity retrieval
• Implement RAG architectures and evaluate LLM tooling suited to use cases
• Build reliable, observable data pipelines with DataOps practices including testing, monitoring, lineage, and SLAs
• Collaborate with Data and Backend Engineers to integrate semantic models into APIs and data contracts
• Partner with the Ontologist to ensure domain-aligned models and support AI-ready data product adoption

• Strong hands-on data engineering experience with semantic or AI data infrastructure
• Experience building/operating knowledge graphs or graph databases (e.g., Jena Fuseki, Neo4j, Amazon Neptune)
• Experience with vector databases and embedding pipelines (e.g., Pinecone, Weaviate, Qdrant, pgvector)
• Practical experience implementing RAG architectures or LLM-integrated data pipelines
• Familiarity with semantic web standards—JSON-LD, RDF, OWL, SKOS
• Strong Python skills and data pipeline frameworks
• Experience with cloud-native data platforms (AWS, Azure, or GCP)

• Knowledge graphs/graph databases
• Embedding pipelines and vector databases
• RAG architectures and LLM-integrated data pipelines
• JSON-LD, RDF, OWL, SKOS
• Python and data pipelines
• Cloud platforms (AWS/Azure/GCP)