Software Engineer – Reinforcement Learning Environments

Job overview

The Software Engineer – Reinforcement Learning Environments role is onsite in San Francisco, CA. Base compensation is $260,000–$290,000 per year, plus profit share and competitive equity. The role supports an applied research lab building datasets, reinforcement-learning environments, and evaluation infrastructure for frontier AI labs. The engineer designs datasets and evaluation methods that shape how frontier models learn. Through experiments, failure-mode analysis, data pipelines, and collaboration with research teams, the role turns training objectives into measurable specifications and outputs that feed into model training.

What you'll do

• Design data slices that expose 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
• develop quantitative frameworks for dataset quality, diversity, and downstream impact
• create and manage real-world and synthetic data pipelines
• translate research teams’ training objectives into data and evaluation specifications.

What we're looking for

Skills & competencies

software engineer

reinforcement learning

rl environments

ai research

evaluation rubrics

data pipelines

rlhf

rlvr

san francisco ca

transparent search group

$260k–$290k base

visa sponsorship

Work arrangement

• Weekend coverage required

Benefits & perks

• Profit share, competitive equity, and direct work with leading AI labs.

Why this role

Visa sponsorship is listed for H-1B, O-1, and OPT. The posting describes profit share of around 150% of base, per the company, and competitive equity.

About the employer

Transparent Search Group is hiring for this role. Industry: Research and Development in the Social Sciences and Humanities. Sector: 54.