Research, RL Scaling

Thinking Machines Lab
San Francisco
Workplace: HybridFull timeUSD 350,000 - 475,000 annuallyFunction: Research & Scientific (R&D)Education: bachelorsSkills: ["Communication","Research judgment","Technical writing"]

Scale reinforcement learning for frontier models by co-designing both the RL training recipe and the systems that run it, with an emphasis on asynchronous RL. Work end-to-end from algorithms to parallelism plans, improving rollout-generation efficiency and its integration with training. Optimize accelerator utilization, memory, communication, and low-precision numerics, and conduct careful empirical science through trusted instrumentation, ablations, and scaling studies.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Thinking Machines Lab
Thinking Machines Lab
3 days ago

Research, RL Scaling

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 20 hours agoStatus: Live

Job Summary

Scale reinforcement learning for frontier models by co-designing both the RL training recipe and the systems that run it, with an emphasis on asynchronous RL. Work end-to-end from algorithms to parallelism plans, improving rollout-generation efficiency and its integration with training. Optimize accelerator utilization, memory, communication, and low-precision numerics, and conduct careful empirical science through trusted instrumentation, ablations, and scaling studies.
Location: San Francisco
Workplace: Hybrid
Employment Type: Full time
Job Function: Research & Scientific (R&D)

Key Responsibilities

  • •Co-design the RL recipe and the systems that run it, validating jointly at frontier scale.
  • •Advance asynchronous RL algorithms and improve rollout generation efficiency integrated with training.
  • •Run frontier-scale RL end to end, bringing up new models and training setups and keeping large runs stable.
  • •Optimize compute and training efficiency across accelerator utilization, memory, communication, and low-precision numerics.
  • •Conduct empirical science with trusted instrumentation, running ablations and scaling studies and writing results clearly.

Pay and Benefits

Salary: USD 350,000 - 475,000 annually
Perks:Health InsuranceDentalVisionPaid LeavePaid ParentalRelocation

Key Requirements

  • •Proficiency in Python and familiarity with at least one deep learning framework (PyTorch, TensorFlow, or JAX), with comfort debugging distributed training code.
  • •Bachelor’s degree or equivalent experience in Computer Science, Machine Learning, Physics, Mathematics, or a related discipline with strong theoretical and empirical grounding.
  • •Ability to clearly communicate complex technical concepts in writing.
  • •Strong research judgment, including clean ablations, honest baselines, and clear technical writing.
Education:Bachelor's in Computer Science, Machine Learning, Physics, Mathematics, or a related discipline
Skills:CommunicationResearch judgmentTechnical writing
Tech Stack:PythonPyTorchTensorFlowJAXSGLangVLLMTokenSpeed

Eligibility

Work Authorization:Sponsorship available.

Company Brief

Thinking Machines Lab
Develops enterprise AI solutions, custom large language models, and ML platforms to help organizations deploy intelligent applications. Services include data engineering, model development, and AI consulting for scale and production readiness.
Industry: AI & Machine Learning
Company Size: Medium (51 to 250 employees)
Growth: Growth Stage Startup
Headquarters: Mumbai, India
Website