Model Engineer, RL Data

Skills

About the Role

You own ambiguous, hard research problems end to end: forming hypotheses, designing experiments, and building the training, eval and data needed to test them. You improve data recipes, define what makes RL data and rewards good, advance post-training recipes for coding and computer-use agents, build evals that expose model weaknesses, and partner with engineers to scale results to frontier training runs.

Requirements

• Experience writing production-quality code in Python, PyTorch, JAX, Rust or C++
• Onsite: must be able to work in person at the Palo Alto office

Responsibilities

• Design and run rigorous experiments that turn research ideas into measurable gains in model capability
• Improve data recipes through data quality, deduplication and mixture experiments
• Define what makes RL data and rewards good, including grader design and preventing reward hacking
• Advance training science from architecture and scaling experiments to post-training recipes
• Build evals and targeted tasks that expose model weaknesses
• Partner with engineers to take results to frontier-scale training runs

Benefits

• Equity
• Comprehensive medical, vision and dental coverage
• 401(k) retirement plan
• Short and long-term disability insurance
• Life insurance
• Various discounts and perks