Research, Tinker, RL Systems

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

Build post-training reinforcement learning (RL) systems for a fine-tuning platform, spanning RL algorithms, numerics, kernels, and end-to-end training pipelines. Work with internal researchers and external partners to co-design whole-stack training approaches, debug RL runs, and optimize stability and performance so users can achieve frontier-level results. Use Python with deep learning frameworks while engaging directly with researchers pushing Tinker to its limits.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Thinking Machines Lab
Thinking Machines Lab
1 day ago

Research, Tinker, RL Systems

✓ Verified Job

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

Source: Company careers pageValidated by: Fursa AI
Last checked: 12 hours agoStatus: Live

Job Summary

Build post-training reinforcement learning (RL) systems for a fine-tuning platform, spanning RL algorithms, numerics, kernels, and end-to-end training pipelines. Work with internal researchers and external partners to co-design whole-stack training approaches, debug RL runs, and optimize stability and performance so users can achieve frontier-level results. Use Python with deep learning frameworks while engaging directly with researchers pushing Tinker to its limits.
Location: San Francisco
Workplace: Hybrid
Employment Type: Full time
Job Function: Research & Scientific (R&D)

Key Responsibilities

  • •Develop frontier customization techniques and help build the post-training engine for Tinker.
  • •Co-design RL algorithms and whole-stack training systems from RL science down to numerics and kernels.
  • •Debug RL runs in real-world deployments and optimize post-training pipelines for performance and reliability.
  • •Collaborate with internal research teams and contribute to open science and external partners.
  • •Engage with Tinker researchers and companies to improve training approaches and enable frontier-level results.

Pay and Benefits

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

Key Requirements

  • •Bachelor’s degree (or equivalent) in Computer Science, Machine Learning, Physics, Mathematics, or a related field with strong theoretical and empirical grounding.
  • •Proficiency in Python and familiarity with deep learning frameworks (PyTorch, TensorFlow, or JAX), including debugging distributed training and writing scalable code.
  • •Clarity in communication, with ability to explain complex technical concepts in writing.
  • •Strong interest in working on Tinker and increasing usefulness and adoption.
  • •Preferred: strong probability, statistics, and ML fundamentals; experience with RL training stability and low-precision (numerics/quantization) for RL.
Experience:Machine learningLLM servingOpen source
Education:
Skills:CommunicationDebuggingProblem-solvingTechnical writing
Tech Stack:PythonPyTorchTensorFlowJAXSGLangVLLMTokenSpeedDistributed trainingQuantization

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