Software Engineer, RL Environments

About the Role

Build data and evaluation systems that shape how advanced AI models learn and improve. You will work with research teams to turn training objectives into practical datasets, experiments, and evaluation specifications.

What You'll Do

• Design data slices across finance, code, and enterprise workflows to reveal meaningful model failure modes.

• 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 approaches to measure dataset quality, diversity, and impact on model alignment and capabilities.

• Create and manage real-world and synthetic data pipelines.

• Collaborate with research teams to translate training objectives into concrete data and evaluation specifications.

What We're Looking For

• One to four years of software engineering experience building reliable data pipelines, experimentation infrastructure, or evaluation systems.

• Strong Python skills and a track record of shipping software and infrastructure.

• Hands-on experience with LLM evaluations, model post-training, reward modeling, RLHF or RLVR, or related machine learning infrastructure.

• Experience creating or evaluating datasets, including assessing quality, diversity, coverage, and downstream model performance.

• Strong experimental judgment, including forming hypotheses, defining metrics, designing controlled experiments, and interpreting noisy results.

• Experience designing data collection strategies and evaluation rubrics for machine learning models.

• Work in AI safety, benchmarking, model evaluation, or open-source evaluation projects is relevant.

Compensation & Benefits

Base salary is $260,000 to $290,000 annually. Visa sponsorship is available.

Location

On-site in San Francisco, California.