Remote Agentic RL Researcher for Frontiers AI Platform

Prime Intellect, Inc.; United States; Hybrid; USD 150,000 - 300,000; Full time

Benefits offered by this job

Cash Compensation Range $150-300k + eq

Flexible Work (SF, NY, London, or rem)

Visa Sponsorship & relocation support

Professional Development budget

Team Off-sites & conference attendance

Job summary

Prime Intellect, Inc. is building open frontier AI infrastructure and RL-enabled agents. This Applied Research role focuses on RL and ML systems across long-horizon tasks and tool use. You will collaborate with application teams and open-source users while advancing reusable environments and evaluation methods.

You will work to analyze results, separating model, data, harness, and infrastructure contributions, and contribute to open-source systems and papers.

Qualifications

• Hands-on RL training experience.
• Experience with scalable ML systems.
• Ability to build and debug model-training loops.
• Strong Python and debugging skills.
• Experience with long-horizon agent environments.

Responsibilities

• Develop RL and ML systems for long-horizon tasks.
• Build reusable environments, harnesses, rewards, and evaluations.
• Collaborate with application teams and open-source users.
• Assess results to separate model, data, harness, and infrastructure contributions.
• Share open-source systems and papers built from research work.

Skills

Reinforcement Learning

Python

ML Systems

Experimentation

Post-Training

Job description

Prime Intellect, Inc. is building open frontier AI infrastructure and RL-enabled agents. This Applied Research role focuses on RL and ML systems across long-horizon tasks and tool use. You will collaborate with application teams and open-source users while advancing reusable environments and evaluation methods.

You will work to analyze results, separating model, data, harness, and infrastructure contributions, and contribute to open-source systems and papers.