RL Engineer

About the Role

Join a small, early-stage team building training data and evaluation infrastructure for advanced AI models. You will design reinforcement learning environments, datasets, and evaluation methods that help models improve across complex, real-world tasks.

What You'll Do

• Design data slices and agent tasks that reveal meaningful model failure modes across areas such as finance, coding, and enterprise workflows.
• Build and refine evaluation rubrics and reward signals for RLHF and RLVR training pipelines.
• Model annotator behavior and run experiments to improve model capabilities.
• Develop quantitative methods for measuring dataset quality, diversity, and impact on model alignment and capabilities.
• Create and manage real-world and synthetic data pipelines.
• Work with research teams to translate training objectives into concrete data and evaluation specifications.

What We're Looking For

• One to eight years of experience as a machine learning or software engineer.
• Experience building reinforcement learning environments, or strong research experience developing agent tasks.
• Strong backend or full-stack engineering skills in Python, TypeScript, or similar languages.
• A computer science degree from a highly regarded institution, or an exceptional record of relevant experience.
• Experience measuring dataset quality and diversity, with AI research, publications, or relevant side projects as valuable signals.
• A bias for action, strong execution, and willingness to take on challenging, detailed work in a fast-moving team.

Compensation & Benefits

Salary range: $260,000 to $290,000 annually. Visa sponsorship is not available.

Location

Remote, with San Francisco, California as the primary location.