RL Environments Specialist

About xAI

xAI builds AI systems that understand the universe and help humanity pursue knowledge. The team is small, flat, and expects initiative and clear communication.

About the Role

Own full RL environment creation for computer-use agents: UI, backend, task generation, and validation.

In this role, you will

• Build sandbox UIs that agents and RL actors interact with.
• Create tasks for those environments and validate completion programmatically.

Qualifications

• React.js expertise (hooks, modern state; TypeScript preferred) with strong UI/UX and code quality.
• Python backend experience (FastAPI, Flask, or Django).
• Docker required; Compose/Kubernetes a plus.
• Clean APIs (REST/GraphQL), relational schemas, and realistic mock data.
• Daily power-user of coding agents/AI assistants (Cursor, Claude, Copilot, Grok, Aider, etc.) plus RL fundamentals (RLHF, PPO, DPO, reward modeling).

Preferred Qualifications

• Detail-oriented reasoning in fast-paced environments.
• Enjoys teaching/learning with teammates and building truth-seeking AI.

Interview Process

• Technical live coding round.
• Hiring manager / final interview.

Compensation and Benefits

USD $35/hour–$100/hour; varies by location and skills/education/experience. Top performers may be considered for MTS roles. Equal opportunity employer.

Full original job post: https://x.com/i/jobs/1982968792897744896