Lead RL Researcher: Clinical Reasoning Environments Remote

True Talent Solutions Partners

United States

Remote

USD 250,000 - 400,000

Full time

7 days ago
Be an early applicant

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

True Talent Solutions Partners is seeking a research-focused engineer to build reinforcement learning environments for clinical reasoning models, linking task design with model training to create reliable decision-support tools.

You will design reward functions, grading rubrics, and LLM judges, and test them for robustness and reward hacking. The role emphasizes end-to-end ownership and close collaboration with clinicians onboarded across North America.

Qualifications

  • PhD in CS/ML or equivalent RL research/industry experience is required.
  • 3+ years of full-time RL research or post-training experience is expected.
  • Hands-on experience building RL environments for evaluation.
  • Proficiency with Python, PyTorch, and Transformers.
  • Experience calibrating reward functions and LLM judges, with documentation of experiments.

Responsibilities

  • Build RL environments for clinical reasoning tasks with multi-step processes.
  • Design and calibrate reward functions, rubrics, and LLM judges, test for reward hacking.
  • Own end-to-end workflow from task/data creation to implementation and delivery.
  • Run post-training and evaluation experiments to improve environments.
  • Collaborate with clinicians and leadership to validate model outputs.

Skills

Python
PyTorch
Transformers
Reinforcement learning
LLMs
Reward modeling
Evaluation
Research
Collaboration

Education

PhD in computer science / ML or related field, or 3+ years RL research experience

Tools

Python
PyTorch
Transformers
LLMs
Reward modeling

Job description

True Talent Solutions Partners is seeking a research-focused engineer to build reinforcement learning environments for clinical reasoning models, linking task design with model training to create reliable decision-support tools.

You will design reward functions, grading rubrics, and LLM judges, and test them for robustness and reward hacking. The role emphasizes end-to-end ownership and close collaboration with clinicians onboarded across North America.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Lead RL Environments for Clinical Decision Support - Remote
Lead RL Environments for Clinical Decision Support - Remote

True Talent Solutions Partners • United States

Remote
USD 250,000 - 400,000
Remote RL Engineer for Clinical AI & Decision Support
Remote RL Engineer for Clinical AI & Decision Support

HealthTech Company • United States

Remote
USD 250,000 - 400,000
Remote work
Reinforcement Learning Engineer (Clinical Decision Support)
Reinforcement Learning Engineer (Clinical Decision Support)

Unknown • United States

Remote
USD 120,000 - 180,000
Reinforcement Learning Engineer (Fully Remote)
Reinforcement Learning Engineer (Fully Remote)

Unknown • United States

Remote
USD 120,000 - 180,000
Member of Technical Staff, Reinforcement Learning at True Talent Solutions Partners Remote
Member of Technical Staff, Reinforcement Learning at True Talent Solutions Partners Remote

True Talent Solutions Partners • United States

Remote
USD 250,000 - 400,000
Reinforcement Learning Engineer (Fully Remote)
Reinforcement Learning Engineer (Fully Remote)

HealthTech Company • United States

Remote
USD 250,000 - 400,000
Remote work
Member of Technical Staff, Reinforcement Learning
Member of Technical Staff, Reinforcement Learning

True Talent Solutions Partners • United States

Remote
USD 250,000 - 400,000
Founding RL Engineer - Healthcare AI & Clinical Reasoning
Founding RL Engineer - Healthcare AI & Clinical Reasoning

Biostack • San Francisco (CA)

On-site
USD 200,000 - 350,000
Equity 0.1%-1.0%
401(k) match
Health benefits
+4
Lead Agentic RL Scientist — Remote & Flexible
Lead Agentic RL Scientist — Remote & Flexible

Jobgether • United States

Hybrid
USD 180,000 - 260,000
Remote flexibility
Professional development
Annual bonus
+1
Remote Senior RL Scientist — Agent Design & Training
Remote Senior RL Scientist — Agent Design & Training

Centific Global Solutions, Inc. • United States

Remote
USD 200,000 - 250,000