Role overview
Lead the design and delivery of production AI agents that review medical records and claims, apply coding and clinical guidance, and produce evidence-backed findings suitable for expert scrutiny. You will own a problem area from understanding a business need and defining success measures through technical implementation and demonstrated results, while setting direction for other engineers.
Responsibilities
- Work with clinical, product, and operations partners to clarify ambiguous problems and turn them into measurable technical goals.
- Define evaluation metrics, baselines, and shipping thresholds; build repeatable evaluation tools and data pipelines.
- Plan and sequence initiatives, making scope, dependencies, decision points, and tradeoffs clear to technical and nontechnical stakeholders.
- Set architecture for agent workflows, context handling, model selection, evaluation, and deterministic safeguards.
- Build reliable, citation-grounded systems and improve quality, latency, and operating cost; review designs and code and mentor teammates.
- Present results and explain methods to business and clinical stakeholders, including when findings are challenged.
Requirements
- At least 6 years of applied AI, machine learning, or software engineering experience with a relevant bachelor’s degree or equivalent; alternatively, at least 4 years with a relevant master’s or doctorate.
- Ownership of at least two production systems from an unclear initial problem through measured impact, ideally including an LLM or agent system.
- Demonstrated ability to scope open-ended work, establish success measures, deliver it, and show business results.
- Hands‑on experience designing agent workflows, engineering context and structured outputs, grounding answers in evidence, and investigating failures.
- Strong evaluation discipline, Python skills, and confidence collaborating with domain experts and translating technical decisions for them.
- Familiarity with VS Code and Git workflows, including branches, rebases, worktrees, conflict resolution, and pull requests.
Nice to have
- Experience in healthcare, legal, finance, or another high‑consequence field; ownership of trusted business metrics; long‑context document systems; technical leadership; reasoning models; or production LLM caching, observability, and cost controls.
- Document extraction, vision‑language models, multimodal retrieval, and presenting to executive or external audiences are also useful.
Benefits and work setup
Hybrid work with a preference for in-office collaboration and some flexibility. The listed package includes medical, dental, and vision coverage, FSA/HSA, tuition reimbursement, a 401(k) match, unlimited paid time off, and equity. The stated base salary range is $180,000–$260,000+, depending on level and experience.