Machine Learning Engineer at Pelica Health (YC, healthcare AI)

About Pelica Health. Pelica Health is a Y Combinator backed AI company building the operating system for value-based care. We unify claims, EHR, pharmacy, lab, and ADT data into one live record per member, then put an AI copilot next to every team that depends on it: risk adjustment, Quality and Stars, pharmacy and Part D, provider network, and care management. 175,000+ patients managed live on Pelica today. Founded by former engineering and AI leaders from Google and YouTube. Founder letter: Careers page with apply form: What you will do: Build and own production ML systems end to end (data modeling, feature engineering, training, evaluation, deployment, monitoring). Design data pipelines that turn messy real-world healthcare data into reliable features. Train and evaluate models for ranking, prioritization, and prediction. Deploy models as services or batch jobs with clear versioning and rollback. Make architectural decisions around model choice, evaluation metrics, retraining cadence, and system guardrails. Work directly with co-founders. What we are looking for: 3+ years building and deploying ML in production. Strong foundation in ML for structured (tabular) data: feature engineering, regression or classification, ranking or prioritization. Full ML lifecycle. Solid backend engineering. Good system design instincts. Bonus: healthcare or decision-support systems; LLMs in production (RAG, fine-tuning, structured prompting); model monitoring tooling. Why join: 175,000+ patients managed live on Pelica today. Co-founders built and led large teams at Google and YouTube. Five people, no committees, ship end to end. Further reading: | | (Lalit, CTO) | How to apply: one short form at (name, email, role, resume link). We read every submission within 5 business days and reply from a real founder email. Pay $80,000 to $150,000 per year. Location: San Francisco, CA or fully remote (US only). Type: Contract or full-time. Visa sponsorship available.