Research, Coding Agents

Highlights

• Own full coding post-training stack from data to large-scale RL runs.
• Build sandboxed coding environments and reward signals for training.
• Design evals measuring real-world coding usefulness for everyday use.

What they offer

• health, dental, and vision benefits
• unlimited PTO
• paid parental leave
• relocation support as needed

Ideal candidate

A research-driven engineer who thrives owning open-ended problems and turning real coding pain points into model gains. You care about rigorous experimentation and shipping frontier capabilities.

Requirements

• Strong engineering skills, ability to contribute code and debug in complex codebases
• Proficiency in Python and familiarity with at least one deep learning framework
• Comfortable with debugging distributed training and writing code that scales
• Bachelor's degree or equivalent experience in Computer Science, Machine Learning, Physics, Mathematics, or related discipline
• Clarity in communication, ability to explain complex technical concepts in writing
• Experience building synthetic data pipelines and systems adopted by others
• Experience owning end-to-end cycle of identifying model usability gaps and closing them
• Experience making large-scale agentic RL infrastructure reliable at scale
• Experience improving coding capabilities of a frontier model
• PhD or equivalent industry research experience in relevant discipline