Founding AI Engineer

About

You will own the AI core of an innovative medical practice, building LLM-powered systems for immediate diagnosis and treatment. This role moves beyond chatbots, focusing on high-stakes medical decisions, clinical accuracy, and safety. Working directly with physicians, you will ship production-ready AI that directly impacts patient health outcomes and lives.

Location: San Francisco, USA

Why This Role Is Remarkable

• Ship code that powers real-world medical decisions including prescriptions and lab orders rather than just building demos.
• Join a high-performance founding team led by experienced entrepreneurs who previously scaled a telemedicine company to over $100M in revenue.
• Benefit from significant ownership and career growth, with the potential to lead engineering domains or management as the team scales.

What You Will Do

• Optimize LLM integration and prompt engineering for clinical accuracy, medical insights, and safety-critical diagnosis.
• Architect AI infrastructure including RAG systems, semantic search, and complex memory systems for multi-turn patient conversations.
• Implement medical safety guardrails and evaluation frameworks to eliminate hallucinations and ensure groundedness in high-risk scenarios.

The Ideal Candidate

• 3+ years of software engineering experience with at least 12 months shipping LLM applications to production environments.
• Expert-level Python skills and deep familiarity with token economics, vector databases, and RAG architectures.
• An AI-native builder who uses modern tools like Cursor/Claude daily and prioritizes safety in high-stakes domains.