Member of Technical Staff, Compiler

Role details

ABOUT THE ROLE Join a clinical AI team building a production compiler that turns healthcare standards into structured, executable decision logic. This research-focused engineering role combines rigorous experimentation with production delivery, helping make clinical recommendations traceable, complete, and verifiable. WHAT YOU'LL DO - Build and improve a pipeline for parsing clinical standards, transforming their content, and validating executable modules. - Design and refine a representation for guideline logic, including exclusions, precedence, and recommendations. - Compare open and closed models, fine-tuning approaches, and constrained decoding through well-designed experiments. - Develop benchmarks, datasets, metrics, and adversarial cases to assess source fidelity, logical completeness, and recommendation correctness. - Work with clinicians and technical leaders to investigate model failures and improve the production system. - Develop deterministic validators using static analysis, constraint solving, or formal methods to surface ambiguity and contradiction. WHAT WE'RE LOOKING FOR - At least 3 years of research or industry experience, or final-year PhD or postdoctoral experience. - 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 a clear, evidence-based approach to communicating failed experiments and uncertainty. - A bachelor's degree or higher in computer science, machine learning, mathematics, or a related technical field. - Experience at a frontier AI lab; familiarity with compilers, program synthesis, formal methods, static analysis, IR design, constraint solving, SAT/SMT, or DSLs is valuable. - Healthcare, safety-critical, or regulated-domain experience is beneficial. Must be authorized to work in the United States or Canada, and willing to attend in-person offsites several times per year. - Comfort working through ambiguity and collaborating across disciplines, with a commitment to validating model outputs. COMPENSATION & BENEFITS Base salary: $250,000 to $400,000 USD annually. Visa sponsorship is not available. LOCATION Remote, with the primary location in Canada. Candidates may also work remotely from the United States.