Staff Software Engineer, AI Engineer

Midi Health•San Francisco, CA

8h•Hybrid

About The Position

Midi Health is the largest virtual care clinic for women in midlife navigating perimenopause, menopause, and other hormonal transitions. We combine expert clinicians, evidence-based protocols, and a modern technology platform to deliver care that has historically been underserved by the healthcare system. We're a fast-growing, mission-driven company building the infrastructure and products that define this new category of care. How We Work: Hybrid by design. Two days a week in-office (Tuesday and Thursday) in Palo Alto or San Francisco. We believe high-trust teams are built in person and scaled remotely. AI-native engineering. We expect every engineer to be fluent with modern AI coding tools (Claude Code, Cursor, Copilot, and similar) and to actively push the frontier of how we build software. Low-ego, high-curiosity. We approach disagreement with humility and technical rigor, not politics. We invest in each other's growth. Outcome-oriented. We move fast, own our work end-to-end, and balance speed with the durability that healthcare demands.

Requirements

10+ years of software engineering experience, with deep recent time leading production AI/LLM systems
Seasoned hands-on coder; still writes production Python regularly
Seasoned system designer for AI systems at scale — retrieval, agents, evaluation, latency, and cost
Authority in AI engineering: teams and leaders defer to your judgment, and you can defend it rigorously
Leader at the AI frontier: you set how the team uses AI tooling and how we build AI products
Seasoned mentor; you've grown engineers into strong AI builders
Strong communicator with product, clinical, and executive stakeholders; thoughtful about risk and safety tradeoffs
Low-ego, curious, humble
All Candidates must be authorized to work in the United States without current or future sponsorship needs.

Nice To Haves

Healthcare, clinical NLP, or regulated AI deployment experience
Track record of shipping agentic or large-scale RAG systems in production

Responsibilities

Lead technical strategy for AI/LLM systems across Midi's product surfaces
Architect retrieval, orchestration, agentic, and evaluation systems that run reliably in production
Set the standards for AI safety, evaluation, observability, and responsible rollout in a healthcare context
Partner with clinical, product, and executive leadership to shape the AI roadmap
Mentor senior and mid-level engineers into strong AI engineers; raise the AI literacy of the whole org
Lead the frontier: evaluate new models, techniques, and tools, and bring the right ones into the team