Member of Technical Staff, Compiler

About the Role

Join a healthtech team building a compiler that turns clinical guidelines into structured, executable decision logic. This research-focused role has production engineering stakes: you will evaluate approaches for extracting and validating clinical logic, then ship effective methods into systems used in healthcare.

What You'll Do

• Build a pipeline for parsing clinical documents, transforming guideline content, and validating executable modules.

• Design and refine a target syntax for representing guideline logic.

• Run experiments across open and closed models, fine-tuning approaches, and constrained decoding.

• Co-design benchmarks, datasets, metrics, and error analyses to assess clinical fidelity.

• Work with clinicians and technical leadership to represent exclusions, precedence, and recommendations.

• Create adversarial test cases that measure source fidelity, logical completeness, and recommendation correctness.

• Turn model failures into hypotheses and experiments that improve the production compiler.

• Develop deterministic validators using static analysis, constraint solving, or formal methods.

What We're Looking For

• At least 3 years of research or industry experience, or be a final-year PhD candidate or postdoctoral researcher.

• Experience shipping ML or NLP systems to production, with production-level Python, PyTorch, and Transformers skills.

• Experience with LLM evaluation, training, or prompt engineering, and clear written communication about failed experiments and uncertainty.

• A bachelor's degree or higher in computer science, machine learning, mathematics, or a related technical field.

• Experience working at a frontier AI lab, plus authorization to work remotely in the United States or Canada.

• Background in compilers, program synthesis, formal methods, or static analysis is beneficial, as is experience in healthcare or another regulated or safety-critical domain.

• Knowledge of intermediate representations, constraint solving, SAT/SMT, or domain-specific languages is helpful.

• Comfort with ambiguity, cross-disciplinary collaboration, and attending in-person offsites several times per year.

Compensation & Benefits

Salary range: USD $250,000 to $400,000 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.