Agentic RL Researcher — Open Systems & Tools

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

Benefits offered by this job

Flexible work locations (remote or in‑

Visa sponsorship & relocation support

Professional development budget

Team off-sites & conference attendance

Job summary

Prime Intellect, Inc. is building an open frontier AI platform that unifies compute, environments, evaluations, sandboxes, and deployment for frontier-scale models.

This applied research role focuses on RL and ML systems that enable agents to reason over long horizons, use tools, coordinate with other agents, and learn from experience. You will develop reusable environments and evaluation methods, work with customers and researchers, and contribute to open-source systems and papers that transfer

Qualifications

• Hands-on reinforcement learning training experience.
• Experience building scalable ML systems for research and production.
• Experience with agent-environment simulations and long-horizon reasoning.
• Familiarity with evaluation pipelines and ablation studies.
• Experience with post-training/inference infrastructure in research settings.
• Evidence of interdisciplinary research across methods and systems.
• Proficiency in Python and artifacts that others can run and inspect.

Responsibilities

• Develop RL and post-training methods for tool-using, multi-agent, memory-augmented, long-horizon systems.
• Create reusable environments, harnesses, rewards, and evaluations.
• Run experiments linking algorithm choices to training and inference behavior.
• Open-source systems and papers derived from application research and external users.
• Collaborate with customers, users, and partners while maintaining a research agenda.

Skills

Hands-on RL training

Scalable ML systems

Agent environments

Evaluation

Inference infrastructure

Research across methods

Strong Python

Job description

Prime Intellect, Inc. is building an open frontier AI platform that unifies compute, environments, evaluations, sandboxes, and deployment for frontier-scale models.

This applied research role focuses on RL and ML systems that enable agents to reason over long horizons, use tools, coordinate with other agents, and learn from experience. You will develop reusable environments and evaluation methods, work with customers and researchers, and contribute to open-source systems and papers that transfer