Member of Technical Staff, Compiler

Compiled Health is a clinical AI research company. We are building a future where the standard of care is executable: where what medicine knows is what medicine does, at every visit, in every setting. The accumulated, evidence-graded knowledge of medicine still lives in documents built to be read, not executed. We compile that knowledge into decision artifacts that are measurable against the standard, deterministic where they must be, and traceable to their source evidence. Our compiler is live in clinical production today: clinicians in public health networks act on its recommendations every day. About the Role The compiler is the heart of Compiled Health: the pipeline that converts clinical standards into executable decision artifacts. Our founding thesis is that reasoning does not run on language: however capable frontier models become, the logic reaching a clinical decision must arrive in a form a clinician can inspect. So the models do their heaviest work at compile time, under scrutiny. This is a research role with production stakes. You will study how far frontier models can be pushed in extracting, structuring, and proving clinical logic; design the experiments that settle what works; and ship the winning approach into the pipeline. What you build deploys to real clinics and is validated by clinicians who stake their license on the outputs. What You'll Do Develop the pipeline that converts clinical standards into executable modules: parsing (document and layout models, OCR), transformation, validation. Design and iterate on our target syntax for guideline logic. Run experiments on open vs closed models, fine-tuning, and constrained decoding. Co-design our benchmarks: datasets, metrics, and error analysis for clinical fidelity. Work directly with the founders and the clinicians who validate your outputs. Skills and Qualifications Minimum qualifications: 3+ years shipping ML or ML-adjacent systems to production. Graduate degree in CS, ML, Statistics, or a related field (PhD preferred, or equivalent research or industry experience). Strong Python engineering (testing, modular design) and proficiency with a deep learning framework (PyTorch, Transformers). Extreme ownership of every step of your work. Comfort going 0 to 1 on difficult problems in a small, fast-paced team. Bonus qualifications: Applied research: publications or open-source work. Interest in healthcare or safety-critical systems, and a personal reason to care. Comfort working across the stack to carry research prototypes into production systems. Logistics Location: This role is remote, with offsites multiple times per year. Work authorization: You must be eligible to work in the United States or Canada. We are not able to sponsor visas at this time. Benefits: Compiled Health offers health, dental, and vision benefits, flexible PTO, and paid parental leave. We are an equal opportunity employer and evaluate candidates on merit alone.