Member of Technical Staff, Compiler
Summary
Research-focused compiler engineer at a healthtech company building a production compiler that turns clinical standards into executable, inspectable decision logic for clinical AI systems. Day-to-day involves parsing clinical documents, designing guideline syntax, evaluating and fine-tuning LLMs, building benchmarks, and developing formal validators in Python/PyTorch.
About the Role
Join a healthtech team building a production compiler that turns clinical standards into executable, inspectable decision logic. This research-focused role combines rigorous experimentation with production engineering to improve the reliability and traceability of clinical AI systems.
What You'll Do
Build a pipeline that parses clinical documents, transforms their content, and validates executable modules.
Design and refine 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 for clinical fidelity and recommendation correctness.
Analyze model errors and turn findings into experiments and improvements to the production compiler.
Work with clinicians and technical leaders to make exclusions, precedence, recommendations, and source evidence explicit.
Build deterministic validators using static analysis, constraint solving, or formal methods to identify ambiguity, contradictions, and missing source evidence.
What We're Looking For
At least 3 years of research or industry experience, or current final-year PhD or postdoctoral experience.
Production experience shipping ML or NLP systems, beyond research prototypes.
A bachelor's degree or higher in computer science, machine learning, mathematics, or a related technical field.
Production-level Python, PyTorch, and Transformers ecosystem skills, plus experience with LLM evaluation, training, or prompt engineering.
Ability to clearly document failed experiments, uncertainty, and model limitations, and to validate plausible outputs rather than assume they are correct.
Experience with compilers, program synthesis, formal methods, static analysis, intermediate representations, constraint solving, SAT/SMT, or domain-specific languages is valuable.
Healthcare, safety-critical, or regulated-domain experience is valuable. Familiarity with FHIR or HL7 v2 is also useful.
Comfort working across disciplines and with ambiguity, and willingness to attend in-person offsites multiple times per year.
Must be authorized to work in the United States or Canada. Visa sponsorship is not available.
Compensation & Benefits
Base salary: $250,000 to $400,000 USD annually. Equity details were not provided.
Location
Remote in Canada or the United States. Primary location: Canada.
Skills
As published by ashby · 2 questions
Basics
Name, Email, Resume
Short answers (1)
- LinkedIn Profile URL optional
Pick from a list (1)
- Do you have work authorization for the country this role is based in? optional
