Reinforcement Learning · Python · TensorFlow
ABOUT THE ROLE
Join a healthtech team building clinical decision-support systems for use in public healthcare. You will own reinforcement learning environments and evaluations that help make model behavior more reliable in clinical settings.
WHAT YOU'LL DO
- Build environments for complex clinical reasoning, including multi-step tasks, tool use, state transitions, and measurable outcomes.
- Design and calibrate reward functions, grading rubrics, and LLM judges, and test them for reward hacking and 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 researchers and clinicians to validate model 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.
- At least three years of research or industry experience, or current status as a final-year PhD student or postdoctoral researcher.
- Hands-on experience building reinforcement learning environments for post-training or agent evaluation.
- Production-level Python, PyTorch, and Transformers experience, with familiarity in LLMs, reward modeling, and evaluation.
- Experience owning reward functions, grading rubrics, or LLM-judge calibration, and communicating failed experiments and uncertainty clearly.
- Clinical AI experience is helpful, especially in clini