Reinforcement Learning Environments Engineers

We’re hiring RL Environments Engineers to design and build MLE/SWE environments that deliver high-quality, diverse tasks with minimal supervision. You’ll target specific language models and meet a defined difficulty distribution, delivering about one task every 3–5 hours. Remote contractor role with ≥4 hours overlap to PST and advanced English (C1/C2) required.

Preference Model We Scale AI Agent Infrastructure. We focus on building rigorous environments and evaluations for language models. The company has recently closed a large funding round and is running pilots with leading AI labs.

• Design and build MLE/SWE environments and diverse tasks.
• Target a specified language model and satisfy the required difficulty distribution.
• Deliver ~1 task per 3–5 hours once onboarded.
• Be responsive and edit tasks within 24 hours based on customer feedback.
• Onboard quickly and start delivering on day one; operate with minimal supervision.

Strong Python skills suitable for building RL environments and tasks.

Experience designing environments/tasks for RL or evaluations.

Ability to meet the throughput expectation (1 task / 3–5h) and respond within 24 hours to feedback.

Comfortable onboarding quickly and working independently.

Ability to work with at least 4 hours overlap to PST business hours.

Advanced English (C1/C2) for specifications, reviews, and feedback.

Remote, independent contractor engagement.

Deliverables-driven; begin shipping on day one.