Lead RL Environments for Clinical Decision Support - Remote

True Talent Solutions Partners; United States; Remote; USD 250,000 - 400,000; Full time

Job summary

True Talent Solutions Partners seeks a PhD or experienced RL researcher to own RL environments for clinical decision‑support products. You will design reward structures, grading rubrics, and language model judges, and ensure robust evaluation across post‑training settings.

Responsibilities include end‑to‑end development from data creation to deployment, plus collaboration with clinical experts. Remote work is available for Canada/US applicants.

Qualifications

• PhD in computer science, machine learning, or related field, or at least 3 years of full‑time reinforcement learning research or post‑training experience.
• Hands‑on experience building reinforcement learning environments for post‑training or agent evaluation.
• Production‑level Python, PyTorch, and Transformers ecosystem experience.

Responsibilities

• Own reinforcement learning environments and evaluations for multi‑step clinical reasoning.
• Design and calibrate reward functions and language model judges, test for reward hacking.
• Lead the full loop from task design and data creation to environment implementation and delivery to model training teams.
• Run post‑training and agent evaluation experiments and improve environments from observed failures.
• Collaborate with clinical experts to validate model outputs and improve decision‑support systems.

Skills

Python

PyTorch

Transformers

Education

PhD in CS/ML or related field

Bachelor’s in CS/Math or related field

Tools

Transformers ecosystem

Job description

True Talent Solutions Partners seeks a PhD or experienced RL researcher to own RL environments for clinical decision‑support products. You will design reward structures, grading rubrics, and language model judges, and ensure robust evaluation across post‑training settings.

Responsibilities include end‑to‑end development from data creation to deployment, plus collaboration with clinical experts. Remote work is available for Canada/US applicants.