Member of Technical Staff, Compiler

True; United States; À distance; USD 250 000 - 400 000; Plein temps

Résumé du poste

A health technology team is building a production compiler that turns clinical standards into executable decision logic. This research-focused role blends experimentation with frontier models and hands-on engineering to ensure clinical recommendations are traceable, complete, and verifiable.

You will collaborate with clinicians and technical leadership, design target syntax for guideline logic, run experiments on open and closed models, and develop benchmarks and validators to improve model

Qualifications

• At least 3 years of research or industry experience, or final-year PhD or postdoc, with production engineering experience.
• Experience shipping ML or NLP systems to production with Python, PyTorch, and Transformers.
• Experience with LLM evaluation, training, or prompt engineering.
• Clear technical writing abilities.
• Experience with compilers, program synthesis, formal methods, IR design, constraint solving, SAT/SMT, or DSLs.
• Healthcare, safety-critical, or regulated-domain experience is valuable.
• Familiarity with FHIR or HL7 v2 is relevant.
• Willingness to attend in-person offsites several times per year.

Responsabilités

• Build production pipelines that parse clinical standards and transform them into validated executable modules.
• Design and refine a target syntax for representing guideline logic.
• Run experiments with open and closed models, fine-tuning, and constrained decoding.
• Develop benchmarks, datasets, metrics, and adversarial cases to assess clinical fidelity and recommendation correctness.
• Analyze model errors and turn findings into experiments and improvements to the production compiler.
• Build deterministic validators using static analysis, constraint solving, or formal methods to identify ambiguity, contradictions, and gaps in source material.
• Collaborate with clinicians and technical leadership to validate system outputs.

Connaissances

Python

PyTorch

Transformers

Prompt engineering

LLM evaluation

Compiler design

Formal methods

Constraint solving

FHIR/HL7 v2 familiarity

Formation

Bachelor's degree in Computer Science or related technical field

Outils

OpenAI tools / LLM tooling

Static analysis tooling

SAT/SMT solvers

Constraint solvers

Description du poste

ABOUT THE ROLE

Join a health technology team building a production compiler that turns clinical standards into structured, executable decision logic. This research-focused role combines experimentation with frontier models and hands-on engineering, helping make clinical recommendations traceable, complete, and verifiable.

WHAT YOU'LL DO

• Build production pipelines that parse clinical standards and transform them into validated executable modules.
• Design and refine a target syntax for representing guideline logic.
• Run experiments with open and closed models, fine-tuning, and constrained decoding.
• Develop benchmarks, datasets, metrics, and adversarial cases to assess clinical fidelity and recommendation correctness.
• Analyze model errors and turn findings into experiments and improvements to the production compiler.
• Build deterministic validators using static analysis, constraint solving, or formal methods to identify ambiguity, contradictions, and gaps in source material.
• Collaborate with clinicians and technical leadership to validate system outputs.

WHAT WE'RE LOOKING FOR

• At least 3 years of research or industry experience, or final-year PhD or postdoctoral experience, along with production engineering experience beyond research roles.
• 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 track record of validating model outputs.
• A bachelor's degree or higher in computer science, machine learning, mathematics, or a related technical field.
• Clear technical writing, including the ability to explain failed experiments and uncertainty.
• Experience with compilers, program synthesis, formal methods, static analysis, IR design, 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 relevant.
• Comfort working across disciplines and with ambiguity, and willingness to attend in-person offsites several times per year.

COMPENSATION & BENEFITS

Base salary range: $250,000 to $400,000 USD annually. Visa sponsorship is not available. LOCATION Remote in Canada or the United States. Primary location: Canada.