You'll work across RAG, embeddings, vector databases, knowledge graphs and semantic data, helping build a greenfield AI data platform from the ground up.
What you'll do
- Build and operate AI-ready data pipelines
- Develop embedding and vector search infrastructure
- Build production RAG pipelines for LLM applications
- Implement and maintain knowledge graphs
- Work with semantic models, JSON-LD and RDF
- Build reliable, observable infrastructure for AI workloads
- Work alongside ontologists and AI/data engineering teams
- Experience as an AI Data Engineer
- Strong Python and data engineering skills
- Production experience with RAG, embeddings and vector search
- Pinecone, Qdrant, Weaviate, pgvector or similar
- Neo4j, Neptune, Jena or equivalent graph technology
- JSON-LD, RDF, OWL or SKOS
- AWS, Azure or GCP
Interested? If you're an AI Data Engineer open to hearing about a genuinely greenfield opportunity, get in touch for a confidential conversation.
Message me directly and send through your CV!
