Member of Technical Staff, Compiler

About the Role

Join a healthtech team developing a compiler that turns clinical standards into executable, traceable decision logic used in public healthcare. This research-focused role has production impact, combining experiments with frontier models and engineering work to improve clinical accuracy and reliability.

What You'll Do

• Build and improve pipelines that parse clinical documents and transform standards into validated executable modules.
• Design and iterate on a target syntax for representing guideline logic.
• Evaluate open and closed models, fine-tuning approaches, and constrained decoding strategies.
• Develop benchmarks, datasets, metrics, and adversarial cases to assess clinical fidelity and recommendation correctness.
• Analyze model errors and turn findings into experiments and improvements to the production compiler.
• Create deterministic validators using static analysis, constraint solving, or formal methods to surface ambiguity and contradictions.
• Collaborate with clinicians and technical leaders to validate system outputs and clarify clinical logic.

What We're Looking For

• At least 3 years of research or industry experience, or final-year PhD or postdoctoral experience, with a track record of production engineering beyond research work.
• Experience shipping ML or NLP systems to production and a bachelor's degree or higher in computer science, machine learning, mathematics, or a related technical field.
• Production-level Python, PyTorch, and Transformers experience, plus experience with LLM evaluation, training, or prompt engineering.
• Strong written communication, including the ability to explain failed experiments and uncertainty clearly.
• Experience validating model outputs rather than assuming plausible outputs are correct.
• Compiler, program synthesis, formal methods, static analysis, IR, constraint solving, SAT/SMT, or DSL experience is useful.
• Healthcare, safety-critical, or regulated-domain experience and familiarity with FHIR or HL7 v2 are useful.
• Comfort working across disciplines and with ambiguity, and willingness to attend in-person offsites several times per year.
• Must be authorized to work in the United States or Canada. Visa sponsorship is not available.

Compensation & Benefits

Base salary is $250,000 to $400,000 USD annually. Visa sponsorship is not available.

Location

Remote, with the primary location in Canada. Candidates must be authorized to work in Canada or the United States.