Member of Technical Staff, Reinforcement Learning
New
T
True Talent Solutions PartnersClinical AI
Remote, with the primary location in Canada. Candidates may also be based remotely in the United States.Full-TimeStaff
Salary250,000 - 400,000 USD per year
Apply NowOpens the employer's application page
Job Details
- Experience
- At least three years of full-time reinforcement learning research or post-training experience, or at least three years of research or industry experience; current final-year PhD students or postdoctoral researchers are also considered.
- Required Skills
- PythonPyTorch
Requirements
- Hold a PhD in computer science, machine learning, or a related field, or have at least three years of full-time reinforcement learning research or post-training experience.
- Have at least three years of research or industry experience, or be a final-year PhD student or postdoctoral researcher.
- Have hands-on experience building reinforcement learning environments for post-training or agent evaluation.
- Have production-level Python experience.
- Have production-level PyTorch experience.
- Have production-level Transformers experience.
- Be familiar with LLMs, reward modeling, and evaluation.
- Have experience owning reward functions, grading rubrics, or LLM-judge calibration.
- Communicate failed experiments and uncertainty clearly.
- Be comfortable working across disciplines and validating plausible model outputs.
- Attend in-person offsites multiple times per year.
Responsibilities
- 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.
- Test rewards, rubrics, and judges 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.
- Use experiment failures to improve environments.
- Collaborate with researchers and clinicians to validate model outputs and guide the work.
View Full Description & ApplyYou'll be redirected to the employer's site
