Research Tinker RL Systems
Artificial-intelligence research and product company building customizable AI systems, including the Tinker training API and Inkling open-weight models.
Funding history
About Thinking Machines Lab
Thinking Machines Lab develops AI products that let researchers and developers fine-tune and use models, while also releasing open-weight multimodal models.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will develop model-customization techniques and training systems for post-training, including reinforcement-learning systems, numerics, and kernels. You will co-design algorithms and systems across the stack, debug reinforcement-learning runs, optimize pipelines, and work with researchers, companies, external partners, and open-science contributors.
Requirements
- Bachelor’s degree or equivalent experience in Computer Science, Machine Learning, Physics, Mathematics, or a related discipline
- Proficiency in Python
- Familiarity with PyTorch, TensorFlow, or JAX
- Ability to debug distributed training and write scalable code
- Ability to communicate complex technical concepts in writing
- Strong interest in Tinker and increasing its usefulness and adoption
Responsibilities
- Develop frontier model-customization techniques and post-training systems
- Build reinforcement-learning systems, numerics, kernels, and related training infrastructure
- Co-design reinforcement-learning algorithms and training systems across the stack
- Debug reinforcement-learning runs and optimize post-training pipelines
- Work directly with researchers and companies using Tinker
- Contribute to open science and collaborate with external partners
Benefits
- Health benefits
- Dental benefits
- Vision benefits
- Unlimited PTO
- Paid parental leave
- Relocation support
- Visa sponsorship