Agentic AI/LLM Engineer, Coverage Intelligence

YOUR ROLE

As an Agentic AI / LLM Engineer on the Coverage Intelligence team, you design and build the AI systems that turn complex insurance documents into reliable, explainable coverage intelligence inside the Digital Exchange, powered by DeX ai. You own problems end to end, from understanding unstructured documents to building agents that reason about coverage, and you hold that work to a measurable standard of accuracy. You work alongside our coverage and ontology specialists and help shape how the team builds with AI as the technology evolves.

WHAT YOU'LL DO

• Design, build and own production AI systems for document understanding and coverage analysis.
• Build agentic workflows that combine models, tools and human review, and recognize when a decision needs an expert.
• Ground outputs in source documents and domain knowledge so every result is traceable and explainable.
• Drive accuracy through evaluation, experimentation and error analysis against expert-labeled data.
• Make sound trade-offs across models and providers on accuracy, cost and latency.
• Partner with domain experts and engineers to turn expert judgment into durable system behavior.
• Help set the team’s technical direction as LLM and agent capabilities evolve.
• Other duties and responsibilities as assigned.

SKILLS AND QUALIFICATIONS

• 5+ years’ experience in software engineering or applied machine learning, including 2+ years building LLM applications in production.
• Strong Python skills, including typed schemas for structured output (e.g., Pydantic).
• Hands-on experience extracting structured data from complex documents using PDF parsing, OCR and vision-language models.
• Experience with agentic patterns such as tool use, multi-step workflows, self-verification and human-in-the-loop review.
• Experience with retrieval-augmented generation, embeddings and source-grounded output.
• A rigorous approach to evaluation: defining metrics, building test sets and doing systematic error analysis.
• Excellent written and verbal communication skills, including working directly with domain experts.
• Works autonomously with minimal direction, sets a clear path through ambiguity, and holds a high bar for quality.
• Thrives on the energy of a start up: comfortable with pace, changing priorities, and building the function while running it.
• Experience with insurance, legal, financial or other contract-heavy documents (strongly preferred).
• Experience with LangGraph or similar agent frameworks (preferred).
• Experience with LLM observability and evaluation tooling (preferred).