Client Roles
ABOUT THE ROLE
Build reinforcement learning environments and evaluation systems for clinical reasoning models. This hands-on research role connects task and reward design with model training, helping create reliable decision-support tools for healthcare.
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 the full workflow from task design and data creation through implementation, evaluation, and delivery to model-training teams.
- Run post-training and agent-evaluation experiments, using observed failures to improve environments.
- Collaborate with clinicians and research leadership to validate model outputs.
WHAT WE'RE LOOKING FOR
- A PhD in computer science, machine learning, or a related field, or at least three years of full-time experience in reinforcement learning research or post-training.
- 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 comparable AI organization.
- Production-level Python, PyTorch, and Transformers experience, plus familiarity with LLMs, reward modeling, and evaluation.
- Experience owning reward functions, grading rubrics, or LLM jud