ML Engineer, Retrieval & Grounded Generation
Benefits
Unlimited PTO
Similar Jobs
See allForward-Deployed Engineer
Acceler
LLM
RAG
Python
Sr. Machine Learning Engineer (Remote, Contract)
Smart Working
Pakistan
Python
MLOps
Machine Learning
Senior AI Engineer – Agentic Systems & LLM Applications
Jobgether
Global
Python
TypeScript
LangChain
AI Engineer - L3
Korza
Python
LLMs
Senior AI Solutions Engineer, Data Science
Penguin Random House
Python
RAG
LLM
About the Role:
- Work on a production system that pulls together records from dozens of external feeds, resolves them to the right person, and surfaces what a human reviewer should look at first.
- Own the retrieval and grounded generation stack, from embeddings and vector storage to prompt design and model serving.
- Operate inside a secure government cloud environment, with a focus on testable citation paths and reliable rollback.
Key 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 and citation failures are tested for.
- Own model packaging, versioning, serving, and rollback, plus telemetry for retrieval and generation quality.
What We Offer:
- A fully remote, results-based environment with a competitive salary, bonus, and equity package.
- 100% employer-paid health insurance including medical, dental, and vision, plus unlimited PTO and 14 weeks of fully-paid parental leave.
DEFCON AI
DEFCON AI is an insights company that leverages artificial intelligence, mathematical optimization, data analytics, and software engineering to build resilient optimization systems for complex operations. The company offers a fully remote, results-based environment with a focus on production systems and a strong benefits package.