About the role

Clinical AI researcher building a deterministic, evidence-traceable compiler for Canadian healthcare standards. Developing model pipelines, formal validators, and executable clinical decision logic.

Responsibilities

Study how far frontier models can be pushed in extracting, structuring and proving clinical logic
Design experiments to determine what works
Ship the winning approach into the clinical compiler
Build the pipeline converting clinical standards into executable modules using parsing, document and layout models, transformation, and validation
Design and iterate the target syntax/representation for guideline logic, including exclusions, precedence, and recommendations
Run experiments involving open versus closed models, fine-tuning, and constrained decoding
Co-design benchmarks and adversarial cases measuring source fidelity, logical completeness, and recommendation correctness
Perform error analysis
Develop deterministic validators using static analysis, constraint solving, or formal methods to surface ambiguity, contradiction, and source silence
Work directly with founders and clinicians who validate outputs
Turn model failures into hypotheses and improved system design

3+ years of research or industry experience, or final-year PhD / postdoc
Published in clinical AI (strongly preferred)
Python
PyTorch
Transformers/LLMs
Static analysis
SMT/SAT solvers
FHIR / HL7 v2 a plus
Based in the US or Canada
US citizen/Green Card
Visa sponsorship is not offered, with possible exceptions for frontier-lab employees

Competitive equity (up to 5% for a frontier-lab candidate, from a 15% pool; cash/equity ratio flexible)
Health insurance
Dental insurance
Vision insurance
Flexible PTO
Paid parental leave
Company offsites several times a year