Member of Technical Staff, Reinforcement Learning
- Same title, closed before
- ×1
- Opened · 30d
- +48
- Closed · 30d
- −57
- All software engineering
- 74,987open
About the Role
Join a healthtech team building decision-support tools for clinical care. You will own reinforcement learning environments and evaluations that help training teams develop systems for complex clinical reasoning, with work informed by clinical experts.
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 language model judges, and test them for reward hacking and misleading scores.
Own the full loop from task design and data creation through environment implementation, evaluation, and delivery to model-training teams.
Run post-training and agent evaluation experiments, then use observed failures to improve environments.
Collaborate with clinical experts to validate model outputs and improve the quality of decision-support systems.
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.
At least three years of research or industry experience, or current status as a final-year PhD candidate or postdoctoral researcher.
Hands-on experience building reinforcement learning environments for post-training or agent evaluation, ideally in a frontier AI lab or leading AI company.
Production-level Python, PyTorch, and Transformers ecosystem experience.
Experience owning reward functions, grading rubrics, or language model judge calibration.
A bachelor's degree or higher in computer science, machine learning, mathematics, or a related technical field.
Ability to communicate failed experiments and uncertainty clearly, validate plausible model outputs, and work across disciplines in ambiguous settings.
Clinical AI experience is useful, as is knowledge of information retrieval design, constraint solving, SAT/SMT, or domain-specific languages.
Authorization to work remotely in Canada or the United States, and willingness to attend in-person offsites several times a year.
Compensation & Benefits
Base salary: $250,000 to $400,000 USD annually. Visa sponsorship is not available.
Location
Remote, with the primary location in Canada. Candidates must be authorized to work in Canada or the United States.