Research, Tinker, RL Systems
Thinking Machines LabSan FranciscoOn-Site
Needs a free Superjobs account. You'll finish on Thinking Machines Lab's Ashby page.
Skill score
Summary
This person builds and improves the training systems behind Tinker, a fine-tuning API, including RL algorithms, numerics and kernels. They debug RL runs, optimize post-training pipelines, and work with researchers and external partners to help users reach frontier-level results.
- Estimated salary
- Est. $102k–153k/yr
- Estimated for a mid-level role, ~3 yrs experience (typical for the level), United States. Not published by the employer.
- Work mode and location
- On-Site, San Francisco
- Employment type
- Full-time
Job description
Overview
Tinker is our fine-tuning API that empowers researchers and developers to customize frontier AI to their needs to open access to capabilities that have previously been concentrated in a handful of labs. We manage the infrastructure while allowing Tinkerers full flexibility in training models with their own data, algorithms, and for their own needs.
This role is all about building our training systems for Tinker, including RL systems, numerics, kernels, and beyond.
Roles and responsibilities
In this role, you'll develop frontier customization techniques and help build the best post-training engine in the industry, drawing on a whole-stack understanding recipes, data pipelines, and training systems (numerics, kernels, and beyond).
You'll engage directly with the researchers and companies pushing Tinker to its limits. This role is working with both our internal research teams as well as contributing to open science and external partners.
You’ll co-design RL algorithms and training systems across the whole stack, from RL science down to numerics and kernels, to enable anyone to post-train frontier models. You’ll debug RL runs in the wild, optimize post-training pipelines, and help users reach frontier-level results, which in turn makes our platform and models the best they can be.
Skills required
Top skills
- Python
- Deep learning frameworks
- PyTorch, TensorFlow, or JAX
- Distributed training
All skills (8)
- Technical writing
- Reinforcement learning
- Probability and statistics
- RL training stability
- Low-precision training and quantization
- LLM serving stacks
- Scaling studies
- Open-source ML frameworks
Qualifications
Required qualifications
- Bachelor’s degree or equivalent experience in Computer Science, Machine Learning, Physics, Mathematics, or a related discipline with strong theoretical and empirical grounding.
- Proficiency in Python and familiarity with deep learning frameworks (e.g., PyTorch, TensorFlow, or JAX). Comfort debugging distributed training and writing code that scales.
- Clarity in communication, an ability to explain complex technical concepts in writing.
- Strong interest in working on Tinker and increasing usefulness and adoption.
Nice to have
- A strong grasp of probability, statistics, and ML fundamentals. You can look at experimental data and distinguish between real effects, noise, and bugs.
- Experience with RL training stability techniques for large runs.
- Familiarity with low-precision training and inference: numerics, quantization, and their implications for RL.
- Hands-on work with LLM serving stacks (e.g., SGLang, vLLM, TokenSpeed, or custom engines).
- Experience with scaling studies for large models.
- Contributions to open-source training or inference frameworks.
- PhD in Computer Science, Machine Learning, Physics, Mathematics, or a related discipline with strong theoretical and empirical grounding; or, equivalent industry research experience.
Other details
- Location: This role is based in San Francisco, California.
Compensation
- Compensation: Depending on background, skills and experience, the expected annual salary range for this position is $350,000 - $475,000 USD.
- Visa sponsorship: We sponsor visas. While we can't guarantee success for every candidate or role, if you're the right fit, we're committed to working through the visa process together.
Benefits
- Benefits: Thinking Machines offers generous health, dental, and vision benefits, unlimited PTO, paid parental leave, and relocation support as needed.
Company info
About Thinking Machines Lab
Thinking Machines Lab is an artificial intelligence research and product company that builds AI systems meant to be more widely understood, customizable, and generally capable. It offers Tinker, an API for fine-tuning open weights models, and its work is aimed at researchers and people who want to adapt AI to