Software Engineer - RL Environments

Company: Confidential - Fast-growing applied AI research lab
Location: San Francisco, CA (in person)
Compensation: $260,000 - $290,000 base + profit share (around 150% of base, per the company) + competitive equity
Employment Type: Full-time
Visa Sponsorship: H-1B, O-1, OPT

About the Company

An applied research lab that builds the datasets, reinforcement-learning environments and evaluation infrastructure that frontier AI labs use to train better models. Founded recently, it has grown to a nine-figure revenue run rate.

The Role

As a Software Engineer on Environments, you will design the datasets and evaluation rubrics that directly shape how frontier models learn. You will work hands-on with research teams at top AI labs, experiment with data-collection strategies, diagnose model failure modes and build metrics that show whether a model is actually improving, moving from hypothesis to live experiment quickly, with output feeding directly into training runs at scale.

What You Will Do

• Design data slices that expose meaningful model failure modes across domains such as finance, code and enterprise workflows.
• Build and refine evaluation rubrics and reward signals for RLHF and RLVR pipelines.
• Model annotator behavior and run experiments to improve model capabilities.
• Develop quantitative frameworks for dataset quality, diversity and downstream impact on alignment and capability.
• Create and manage real-world and synthetic data pipelines.
• Translate lab research teams' training objectives into concrete data and evaluation specifications.

What You Bring

• 1-4 years of engineering experience
• Strong software engineering fundamentals and comfort running fast, hypothesis-driven experiments
• Interest in RL, evaluation and data for frontier model training
• Ability to work in person in San Francisco

Benefits

Profit share (around 150% of base per the company), competitive equity, and direct work with the world's leading AI labs.