Senior Software Engineer, AI Engineer

Midi Health is hiring a Senior Software Engineer, AI Engineer to design, build, and ship LLM-powered capabilities end-to-end, with a focus on evaluation, safety, and practical integration into clinical and operational workflows.

Location and Employment

• Location: San Francisco, CA (hybrid)
• Hybrid schedule: Two days per week in office on Tuesday/Thursday in Palo Alto or San Francisco
• Job type: Full-time W2
• Compensation: USD 170,000 to 210,000 per year

What You Will Do

• Design, build, and ship LLM-powered features end-to-end, including prompt design, retrieval, tool use, agents, evaluation, and production operations
• Build evaluation harnesses and feedback loops to support responsible shipping of AI features
• Integrate AI capabilities deeply into patient, clinician, and operational workflows
• Collaborate with clinical, product, and safety stakeholders to define what “good” looks like
• Contribute to internal AI-for-engineering practices and tooling
• Stay engaged with research and the AI ecosystem and bring useful advances back to the team

Qualifications

• Experience: 6+ years of software engineering, including meaningful recent time building production LLM/ML features
• Coding: strong hands-on coding skills in Python, with comfort across the stack when needed
• AI systems design: system design experience for AI systems such as retrieval, orchestration, caching, evaluation, plus cost and latency tradeoffs
• AI coding tools: deep, hands-on command of modern AI coding tools, with a track record of adopting new techniques quickly
• Mentorship: good mentorship instincts and willingness to share what you learn
• Evaluation and safety: rigorous approach to evaluation and safety, with focus on results over “vibes-only” launches
• Communication: strong communicator able to explain model behavior to non-technical stakeholders
• Collaboration style: low-ego, curious, and humble

Technologies

• Python
• LLM
• ML
• Claude Code
• Cursor
• Copilot

Nice to Have

• Experience with healthcare, clinical NLP, or regulated AI deployments
• Experience building agentic systems or production RAG at scale

Interview Process

• Recruiter Screen (30 min)
• Hiring Manager Screen (45 min)
• Live Technical Assessment (3 sessions totaling 150 min)
• On-Site Interview and Lunch (4 sessions totaling 150 min)