Thinking Machines Lab
Research, RL Scaling
$350K–$475K
San Francisco · On-site · Full-time · Posted Aug 21, 2026
- Education
- Bachelor’s degree or equivalent experience in Computer Science, Machine Learning, Physics, Mathematics, or a related discipline; a PhD or equivalent industry research experience is preferred.
- Visa sponsorship
- Visa sponsorship is offered; success is not guaranteed for every candidate or role.
About the job
Researcher who co-designs asynchronous reinforcement learning algorithms and systems, and runs frontier-scale RL training for large models.
What you'll do
- Co-design and validate RL recipes and systems at frontier scale, including asynchronous RL algorithms.
- Improve rollout generation efficiency and jointly optimize compute and training efficiency across accelerators, memory, communication, and low-precision numerics.
- Run and stabilize large-scale RL training; conduct ablations and scaling studies and communicate findings clearly.
What they ask for
- Proficiency in Python and familiarity with at least one deep learning framework (e.g., PyTorch, TensorFlow, or JAX).
- Bachelor’s degree or equivalent experience in Computer Science, Machine Learning, Physics, Mathematics, or a related discipline.
- Ability to debug distributed training and write scalable code.
- Clear technical communication and strong research judgment, including clean ablations and honest baselines.
Nice to have
- PhD in a relevant discipline, or equivalent industry research experience.
- Experience or expertise in asynchronous RL, large-scale model training, inference systems, rollout generation, or related RL methods and infrastructure.
Pay
$350,000 - $475,000 USD (base salary)
Tools
Python, PyTorch, TensorFlow, JAX, SGLang, vLLM, TokenSpeed
AI focus
Scale reinforcement learning for frontier models, including asynchronous RL, efficient rollout generation, and end-to-end training systems.
Model-written summary · the original posting is authoritative