Impress employers and recruiters.
Choose from hundreds of resume examples.

Target Resume Now

About the Role

The Coding Agents team focuses on enhancing AI's ability to perform agentic coding tasks, including writing, debugging, and reasoning about code over extended, multi-turn interactions. You will join a small, high-impact team responsible for the methodologies, data, and infrastructure that drive coding capability improvements in model releases. This team manages the entire post-training coding process, encompassing synthetic and human data generation, RL environments, reward design, and large-scale training.

Responsibilities

Design and execute RL training jobs focused on agentic coding capabilities, refining methodologies and data.
Develop and enhance the sandboxed coding environments and reward mechanisms used for model training and evaluation.
Generate and curate high-quality synthetic coding data, and construct scalable, general-purpose data pipelines.
Design evaluations to measure real-world coding utility and train models against them to achieve tangible improvements in daily usability.
Analyze large RL runs to identify and address issues such as confounders, reward hacking, and other RL failure modes.
Collaborate with infrastructure, evaluation, and other post-training teams on shared data, joint training runs, and usability enhancements, integrating results into model releases.

Requirements

Strong engineering skills with the ability to contribute code and debug complex codebases.
Proficiency in Python and familiarity with at least one deep learning framework (e.g., PyTorch, TensorFlow, or JAX).
Comfortable with debugging distributed training and writing scalable code.
Bachelor’s degree or equivalent experience in Computer Science, Machine Learning, Physics, Mathematics, or a related discipline with strong theoretical and empirical grounding.
Clear communication skills, with the ability to explain complex technical concepts in writing.
Experience building synthetic data pipelines and systems that were adopted by others and remain in use.
Experience managing the end-to-end process of identifying model usability gaps and addressing them through custom evaluations and training data.
Experience ensuring the reliability of large-scale agentic RL infrastructure, accounting for long-tail failures.
Experience improving the coding capabilities of a frontier model.
PhD in Computer Science, Machine Learning, Physics, Mathematics, or a related discipline with strong theoretical and empirical grounding; or, equivalent industry research experience.

Skills

Python
Deep learning frameworks (PyTorch, TensorFlow, JAX)
Distributed training
Scalable code development
Synthetic data pipeline development
Agentic RL infrastructure
Model usability evaluation
Communication

Location

San Francisco, California

Work Type

Full-time

Experience Level

Research role with ownership
Industry research experience

Education Level

Bachelor's degree or equivalent experience in Computer Science, Machine Learning, Physics, Mathematics, or a related discipline
PhD in Computer Science, Machine Learning, Physics, Mathematics, or a related discipline

Salary/Compensations

$350,000 - $475,000 USD

Benefits

Generous health, dental, and vision benefits
Unlimited PTO
Paid parental leave
Relocation support

About the Company

The mission of Thinking Machines is to build AI that extends human will and judgment.
We are training frontier models with Inkling, developing Tinker to let people make models their own, and crafting interfaces that broaden human-AI communication.
We believe the future worth building is human, and we're hiring people who want to build it.

Equal Opportunity

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.