reinforcement learning · healthtech
ABOUT THE ROLE
Build reinforcement learning environments and evaluations for a healthtech team developing clinical decision support tools. You will own the work from task design and data creation through environment implementation and delivery to model-training teams, helping make clinical AI more reliable in practice.
WHAT YOU'LL DO
- Build environments for complex clinical reasoning, including multi-step tasks, tool use, state transitions, and measurable success criteria.
- Design and calibrate reward functions, grading rubrics, and LLM judges, and test them for reward hacking or misleading scores.
- Own task design, data creation, environment implementation, evaluation, and delivery to model-training teams.
- Run post-training and agent evaluation experiments, then use failures to improve environments.
- Collaborate with clinicians and technical leadership to validate model outputs and evaluation quality.
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 final-year PhD or postdoctoral status, with a bachelor's degree or higher in a relevant technical field.
- 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 experience, plus experience with LLMs, post-training, and evaluation.
- Experie