ML Engineer, Retrieval Specialist

Job Summary

To support a dynamic analytics and AI engineering team, the full-time remote ML Engineer, Retrieval Specialist will implement embeddings and vector storage, integrate language models for citation accuracy, and design prompts and output schemas within a secure government cloud environment.

Key Responsibilities

• Implement embeddings, vector storage, and retrieval across a large, provenance-tracked evidence base
• Integrate language models to ensure generated text is bound to cited source records and test for citation failures
• Design prompts and output schemas, and own model packaging, versioning, serving, and rollback

Required Qualifications

• 5+ years of experience with a production or near-production retrieval-augmented (RAG) system you built yourself
• Strong Python skills with hands-on experience in embeddings and vector retrieval at scale
• Ability to provide detailed explanations of retrieval design, vector store choices, and citation testing
• U.S. Citizenship required
• Active U.S. Secret clearance required to start