Remote ML Engineer, Retrieval & Grounded Generation (RAG)

DEFCON AI, Inc.; Northern (KY); Hybrid; USD 165,000 - 200,000; Full time

Benefits offered by this job

Fully remote

Salary, bonus, and equity package

Health insurance (family)

Unlimited PTO

14 weeks parental leave

Flexible work environment

Job summary

DEFCON AI is seeking an experienced ML Engineer, Retrieval & Grounded Generation to design and implement embeddings, vector storage, and retrieval at scale within a secure government cloud environment.

You will integrate language models to bind generated text to cited records, design prompts and output schemas, and own packaging, versioning, serving, and telemetry to enable measurement without manual reconstruction. This is a fully remote role with occasional travel.

Qualifications

• 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
• 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
• Active US Secret clearance required to start.

Responsibilities

• 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
• Design prompts and output schemas
• Own model packaging, versioning, serving, and rollback
• Instrument telemetry for retrieval and generation quality, attribution, overrides, grounding failures, latency, throughput, and measurement events
• Provide bounded model assistance for difficult narrative extraction where deterministic processing is insufficient, with every output tied to its source passage
• Supply the recorded rule context to every model-assisted step, so each output carries the exact rule versions and ordered context it received
• Maintain a modular in-boundary serving path, self-hosted or managed, alongside the primary managed inference service, so the platform does not depend on one provider’s availability or approval

Skills

RAG systems

Retrieval design

Python proficiency

Shipped code

Security clearance

Vector retrieval

Job description

DEFCON AI is seeking an experienced ML Engineer, Retrieval & Grounded Generation to design and implement embeddings, vector storage, and retrieval at scale within a secure government cloud environment.

You will integrate language models to bind generated text to cited records, design prompts and output schemas, and own packaging, versioning, serving, and telemetry to enable measurement without manual reconstruction. This is a fully remote role with occasional travel.