Research Engineer: RL Environments for Frontier AI

Prime Intellect, Inc.; United States; Remote; USD 150,000 - 350,000; Full time

Benefits offered by this job

Quarterly off-sites

Hackathons

Conferences

Learning opportunities

Job summary

Prime Intellect is seeking researchers to work with game-changing AI teams to design RL tasks and environments for training frontier models. You will build executable setups with clear success criteria and investigate model failures to guide improvements.

The role offers remote or in-person work in San Francisco with visa sponsorship and relocation support. You will join a mission-driven team advancing open AI infrastructure with competitive compensation and opportunities to attend conferences

Responsibilities

• Build executable environments with realistic task setup and clear success criteria.
• Trace failures through model outputs and harness code to distinguish model limitations from environment or scoring issues.
• Build and scale RL data pipelines that generate and curate challenging coding and agentic tasks.

Job description

Prime Intellect is seeking researchers to work with game-changing AI teams to design RL tasks and environments for training frontier models. You will build executable setups with clear success criteria and investigate model failures to guide improvements.

The role offers remote or in-person work in San Francisco with visa sponsorship and relocation support. You will join a mission-driven team advancing open AI infrastructure with competitive compensation and opportunities to attend conferences