Remote Agentic RL Researcher for Multi-Agent Systems

Prime Intellect, Inc.; New York (NY); Remote; USD 150,000 - 300,000; Full time

Benefits offered by this job

Equity incentives

Flexible work location

Professional development budget

Job summary

Prime Intellect, Inc. is seeking an Applied Researcher to advance RL and ML systems for long-horizon, tool-using agents.

You will work across algorithms, environments, and evaluation pipelines, collaborating with customers, partners, and open-source users while driving scalable experiments and reproducible results. The role emphasizes cross-domain methods, reusable research artifacts, and contributions to open-source platforms used to push frontier AI forward.

Qualifications

• Hands-on RL training and scalable ML systems experience.
• Experience building/balancing agent environments and evaluations.
• Strong Python and ability to build reusable artifacts.
• Comfort with ambiguous problems and cross-team communication.
• Evidence of exceptional work via publications, OSS, benchmarks.

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 connecting algorithm choices to training and inference behavior.
• Ship open-source systems and papers from application research.

Skills

RL training

ML systems

Agent environments

Evaluation

Infrastructure

Python

Research across domains

Job description

Prime Intellect, Inc. is seeking an Applied Researcher to advance RL and ML systems for long-horizon, tool-using agents.

You will work across algorithms, environments, and evaluation pipelines, collaborating with customers, partners, and open-source users while driving scalable experiments and reproducible results. The role emphasizes cross-domain methods, reusable research artifacts, and contributions to open-source platforms used to push frontier AI forward.