Member of Technical Staff, Compiler

Job description

About the Role

Join a health technology team building a production compiler that turns clinical standards into verified, traceable decision logic. This research-focused engineering role combines experiments with frontier models and the delivery of reliable systems used in public healthcare.

What You'll Do

• Build pipelines that parse clinical standards, transform their content, and validate executable modules.
• Design and refine a representation for clinical guideline logic, including exclusions, precedence, and recommendations.
• Compare open and closed models, fine-tuning approaches, and constrained decoding through structured experiments.
• Develop benchmarks, datasets, metrics, and adversarial cases to assess clinical fidelity and logical completeness.
• Analyze model errors and turn findings into hypotheses, experiments, and improvements to the production compiler.
• Create deterministic validators using static analysis, constraint solving, or formal methods to expose ambiguity, contradictions, and missing source guidance.
• Collaborate with clinicians and technical leadership to validate outputs and guide system design.

What We're Looking For

• At least 3 years of research or industry experience, or final-year PhD or postdoctoral experience, with substantial production engineering experience.
• Experience shipping ML or NLP systems to production and evaluating, training, or prompting large language models.
• Production-level Python, PyTorch, and Transformers ecosystem skills.
• A bachelor's degree or higher in computer science, machine learning, mathematics, or a related technical field.
• Clear technical writing about failed experiments, uncertainty, and model limitations, with a practice of validating plausible outputs.
• Background in compilers, program synthesis, formal methods, static analysis, intermediate representations, constraint solving, SAT/SMT, or domain-specific languages is valuable.
• Healthcare, safety-critical, or regulated-industry experience and knowledge of FHIR or HL7 v2 are valuable.
• Comfort working across disciplines and with ambiguity, and willingness to attend in-person offsites several times per year.
• Authorized to work remotely in the United States or Canada.

Compensation & Benefits

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

Location

Remote in Canada or the United States. Primary location: Canada.