Remote/Flexible Applied RL Researcher — Agentic AI

Prime Intellect, Inc.; San Francisco (CA); Remote; USD 150,000 - 300,000; Full time

Benefits offered by this job

Flexible work (SF, NY, London, or 100%

Visa sponsorship & relocation support

Professional development budget

Team off-sites & conference attendance

Job summary

Prime Intellect, Inc. is building the open frontier AI platform that unifies compute, environments, evaluations, secure sandboxes, and high-performance training for frontier-scale models.

The role focuses on RL and ML systems that reason over long horizons, use tools, coordinate agents, recover from failure, and improve with experience. You will work with application teams and open-source users while expanding methods and systems that transfer across domains.

Qualifications

• Hands-on RL training experience.
• Experience building scalable ML systems.
• Experience with agent environments, evaluation, and inference infrastructure.
• Ability to conduct research that crosses methods and systems.

Responsibilities

• Own RL and post-training methods for tool-using, multi-agent, memory-augmented, long-horizon systems.
• Develop reusable environments, harnesses, rewards, and evaluations.
• Design experiments linking algorithm choices to training and inference behavior.
• Produce open-source systems and papers from real-world problems surfaced by users.

Skills

Reinforcement learning

ML systems

Agent environments

Evaluation

Inference infrastructure

Research across methods & systems

Tools

Python

Job description

Prime Intellect, Inc. is building the open frontier AI platform that unifies compute, environments, evaluations, secure sandboxes, and high-performance training for frontier-scale models.

The role focuses on RL and ML systems that reason over long horizons, use tools, coordinate agents, recover from failure, and improve with experience. You will work with application teams and open-source users while expanding methods and systems that transfer across domains.