Member of Technical Staff, Reinforcement Learning
True Talent Solutions Partners · On site, Montréal, CA
250.000 - 400.000 USD / Ano · Publicada em 17 de nov. de 2026
Candidatar-se a esta vaga com o Jobrona
Crie a sua conta e carregue o CV. Se esta vaga lhe servir, preparamos e enviamos primeiro esta candidatura e mostramos o que foi enviado.
Sobre a vaga
ABOUT THE ROLE
Join a healthtech team building validated clinical decision artifacts for use in patient care. You will own reinforcement learning environments and evaluations that help model-training teams develop reliable systems for complex clinical reasoning.
WHAT YOU'LL DO
- Build reinforcement learning environments for multi-step clinical reasoning, including tool use, state transitions, and measurable success criteria.
- Design and calibrate reward functions, grading rubrics, and LLM judges, and test them for reward hacking and misleading scores.
- Own the workflow from task design and data creation through implementation, evaluation, and delivery to model-training teams.
- Run post-training and agent evaluation experiments, using failures to improve environments.
- Collaborate with clinicians and research leaders to validate model outputs and evaluation methods.
WHAT WE'RE LOOKING FOR
- At least 3 years of research or industry experience, or experience as a final-year PhD candidate or postdoctoral researcher; depth in reinforcement learning research or post-training is valued.
- A bachelor's degree or higher in computer science, machine learning, mathematics, or a related technical field, with a PhD in a related field or at least 3 years of full-time RL research or post-training experience.
- Hands-on experience building reinforcement learning environments for post-training or agent evaluation, plus production-level experience with Python, PyTorch, and Transformer models.
- Experience owning reward functions, grading rubrics, or LLM-judge calibration, and clearly documenting failed experiments and uncertainty.
- Clinical AI experience is useful, particularly in clinical reasoning, longitudinal records, or medical workflows. Knowledge of information retrieval, constraint solving, SAT/SMT, or domain-specific languages is also useful.
- Comfort working across disciplines and with ambiguity, validating plausible model outputs, and attending in-person offsites several times per year.
- Must be authorized to work remotely in the United States or Canada.
COMPENSATION & BENEFITS
Salary range: $250,000 to $400,000. Visa sponsorship is not available.
LOCATION
Remote, with a primary location in Montreal, Quebec, Canada. In-person offsites take place several times per year.