Senior Member of Technical Staff, Compiler

About the Role

Join a clinical AI team building a compiler that turns healthcare standards into executable, traceable decision logic. This research role combines rigorous experimentation with production engineering, helping make clinical recommendations inspectable and reliable in real-world care.

What You'll Do

• Build a pipeline to parse clinical standards and transform them into validated executable modules.

• Design and refine a representation for clinical guideline logic, including exclusions, precedence, and recommendations.

• Evaluate open and closed models, fine-tuning approaches, and constrained decoding techniques.

• Develop benchmarks, datasets, metrics, and adversarial cases to assess source fidelity, logical completeness, and recommendation correctness.

• Work with clinicians and technical leaders to validate outputs and identify meaningful failure modes.

• Develop deterministic validators using static analysis, constraint solving, or formal methods to surface ambiguity, contradictions, and missing source guidance.

• Translate model failures into hypotheses, experiments, and improvements to a compiler operating in clinical production.

What We're Looking For

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

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

• Production experience shipping ML or NLP systems, with strong Python, PyTorch, and Transformers ecosystem skills.

• Experience with LLM evaluation, training, or prompt engineering, ideally including work in a frontier AI lab.

• Clear written communication about uncertainty and failed experiments, and a careful approach to validating model outputs.

• Experience with compilers, program synthesis, formal methods, static analysis, IR design, DSLs, or SAT/SMT solvers is valuable.

• Healthcare, safety-critical, or regulated-domain experience is helpful; familiarity with FHIR or HL7 v2 is also relevant.

• Comfort working across disciplines and with ambiguity, and willingness to attend in-person offsites several times per year.

Compensation & Benefits

Compensation is USD 250,000 to 400,000 annually. Visa sponsorship is not available.

Location

Remote, with the primary location in Canada. The role is open to candidates authorized to work remotely in Canada or the United States.