Machine Learning Engineer (Retrieval & Grounded Generation)

Join our team as a Machine Learning Engineer specializing in Retrieval & Grounded Generation. In this role, you will build embeddings, vector storage, and retrieval at scale, and integrate language models to ensure generated text is bound to cited source records. You will also design prompts and output schemas, own model packaging, versioning, serving, and rollback, and instrument telemetry for retrieval and generation quality. Success in this role will be measured by the accuracy of generated explanations, the performance of the retrieval system, and the effectiveness of model rollback.

• Implement embeddings, vector storage, and retrieval across a large, provenance-tracked evidence base.
• Integrate language models so generated text is bound to cited source records; test for citation failures rather than assuming them away.
• Own model packaging, versioning, serving, and rollback; instrument telemetry for retrieval and generation quality.

• Strong Python, with hands-on experience in embeddings and vector retrieval at scale
• Clarity on what actually shipped in past work — prototype, proposal, or deployed code — since that distinction matters more here than the title on a resume
• 5+ years of experience, including a production or near-production retrieval-augmented (RAG) system you built yourself
• Ability to speak in detail to your retrieval design, which vector store you used and why, how you tested grounding, what citation failures looked like in practice, and how rollback worked
• Active US Secret clearance required to start
• US Citizenship Required
• Experience deploying models into restricted or air-gapped environments
• Self-hosted or open-weight model operation
• Fine-tuning, adapters, or custom embeddings
• Active Top Secret clearance
• Federal DevSecOps, RMF, ATO, or DoW cloud environment experience