About MetabodyYour body runs continuously. Your care runs on appointments -- fifteen minutes against half a million minutes of signal a year. The data piles up in apps nobody reads between visits, and by the time anyone looks, the window has closed.Metabody closes the loop. We unify every signal -- wearables, labs, records -- into one longitudinal graph; our AI co-clinician reads it continuously and surfaces what matters; and a licensed provider in any of 50 states is ready to act. Not just a wearable. Not just telehealth. The whole loop, compounding with every outcome.We're early, with real patients across all 50 states and a founding team that's built, shipped, and scaled before. This is a founding-team hire: you'll own a function from day one and set the patterns the next ten people inherit.The RoleYou set the direction for the AI co-clinician ("Aria") -- the system that reads every patient's longitudinal graph continuously and surfaces what matters, always cited, always grounded in the record. Orchestrated multi-model and agentic systems that hold up when a real patient is on the other end, not demos.What you'll do- Drive the architecture of the AI co-clinician: orchestrated multi-model pipelines, RAG grounded in the patient's record, agentic workflows that are reliable.- Set technical direction on what's worth building.- Own the evals, observability, and clinical guardrails that catch overconfident output before a patient does.- Be the in-house skeptic on your own systems.What we're looking for- Strong AI/LLM/RAG development experience, proven in production.- Prior experience with machine learning systems, not just today's generative AI.- A demonstrated ability to drive direction on orchestrated multi-model and agentic AI products.- The judgment to design evals and guardrails as first-class parts of the system.- Healthcare domain expertise a plus, not a requirement.Source: https://careers.metabody.ai/open-roles/staff-ai-engineer