Member of Technical Staff, Reinforcement Learning
True Talent Solutions Partners
- Remote, US only
- 250,000 - 400,000 USD / Year
- Posted Nov 22, 2026
- ML and AI engineer
- Jobrona can apply for you
About the job
ABOUT THE ROLE
Join a healthtech team developing clinician-facing decision support for public healthcare. You will build reinforcement learning environments and evaluations that help make clinical AI outputs more reliable and useful at the point of care.
WHAT YOU'LL DO
- Design reinforcement learning environments for complex clinical reasoning, including multi-step tasks, tool use, state transitions, and measurable outcomes.
- Create and calibrate reward functions, grading rubrics, and language model judges, testing for reward hacking and misleading scores.
- Own the workflow from task design and data creation through environment implementation, evaluation, and delivery to model-training teams.
- Run post-training and agent evaluation experiments, using failures to improve environments.
- Collaborate with clinicians and technical leadership to validate outputs and guide the work.
WHAT WE'RE LOOKING FOR
- A PhD in computer science, machine learning, or a related field, or at least three years of full-time reinforcement learning research or post-training experience. Candidates with at least three years of research or industry experience, or who are final-year PhD students or postdoctoral researchers, are also considered.
- A bachelor's degree or higher in computer science, machine learning, mathematics, or a related technical field.
- Hands-on experience building reinforcement learning environments, post-training systems, or agent evaluations, plus production-level experience with Python, PyTorch, and transformer models.
- Experience owning reward functions, grading rubrics, or language model judge calibration, and clearly communicating failed experiments and uncertainty.
- Research or industry experience at a frontier AI lab or leading AI company, strong cross-disciplinary collaboration skills, and comfort with ambiguity.
- Healthcare AI experience is useful, especially in clinical reasoning, longitudinal records, or medical workflows. Knowledge of information retrieval, constraint solving, SAT/SMT, or domain-specific languages is also relevant.
- Must be authorized to work in Canada without visa sponsorship and have validated plausible model outputs rather than assuming they are correct.
COMPENSATION & BENEFITS
Base salary is $250,000 to $400,000 annually. Visa sponsorship is not available.
LOCATION
Fully remote in Canada.
Not just this job
With the same CV, Jobrona finds jobs like this one and applies to them for you.
Employer responsiveness
Employer responsiveness
Replies to 44% of applications (sample: 9)
Median reply time: 0.4 days
90-day sample, excluding the last 7 days.