Model Engineer, RL Data

Location: Onsite at the Palo Alto office, Palo Alto, California

Annual salary: $160,000–$250,000 USD

Company

Builds super-intelligence systems, including frontier coding agents and models trained with reinforcement learning on real user data.

What you will do

• Design and run rigorous experiments that turn research ideas into measurable model-capability gains.
• Improve reinforcement-learning data recipes through data-quality analysis, deduplication, and mixture experiments.
• Define effective RL data and rewards, including grader design and reward-hacking prevention.
• Advance training science through architecture, scaling, and post-training experiments for coding and computer-use agents.
• Build evaluations and targeted tasks that expose model weaknesses.
• Partner with engineers to transfer promising results from small experiments to frontier-scale training runs.

Requirements

• Must be able to work onsite at the Palo Alto office.
• Experience writing production-quality code in Python, PyTorch, JAX, Rust, or C++.
• Strong background in reinforcement learning and machine-learning fundamentals.
• Experience training large models through pretraining, post-training, or RL.
• Excellent programming and software-engineering skills, with comfort working across the research stack in Python and PyTorch or JAX.
• Original ML work demonstrated through research, open source, or production impact.
• MS or PhD in computer science, machine learning, mathematics, physics, or a related field, or equivalent research experience.

Nice to have

• Experience with RL algorithms for language models, scaling laws, or RL environments and evaluations.
• Experience with distributed training at scale and debugging scale-specific problems.
• Experience training frontier-scale models.
• Ability to own ambiguous research tasks and a research direction end to end with little guidance.
• Strong focus on data quality and willingness to investigate data directly.

Culture & Benefits

• Small-team research environment with end-to-end ownership of difficult, ambiguous problems.
• Equity and comprehensive medical, vision, and dental coverage.
• Access to a 401(k) retirement plan.
• Short- and long-term disability insurance, life insurance, discounts, and other perks.