Research Coding Agents
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 design and run reinforcement-learning training for agentic coding, improve sandboxed coding environments and reward signals, and build synthetic-data pipelines. You will create evaluations of practical coding usefulness, analyze large-scale training failures, collaborate on shared training work, and deliver results into model releases.
Requirements
- Strong engineering skills and ability to debug complex codebases
- Proficiency in Python
- Familiarity with PyTorch, TensorFlow, or JAX
- Ability to debug distributed training and write scalable code
- Ability to explain complex technical concepts in writing
Responsibilities
- Design and run reinforcement-learning training jobs for agentic coding
- Build and improve sandboxed coding environments and reward signals
- Generate and curate synthetic coding data
- Build scalable data pipelines
- Design coding evaluations and train models to improve usability
- Debug and analyze large reinforcement-learning runs for confounders, reward hacking, and failure modes
- Collaborate on shared data, training runs, and model releases
Benefits
- Health, dental, and vision benefits
- Unlimited PTO
- Paid parental leave
- Relocation support