Remote Applied RL Researcher — Agentic & Multi-Agent Systems

Prime Intellect, Inc.; San Francisco (CA); Hybride; USD 150 000 - 300 000; Plein temps

Avantages offerts par ce poste

Cash compensation range: $150-300k + 0

Flexible work locations: SF, NY,London

Visa Sponsorship & relocation support

Professional Development budget

Team Off-sites & conference attendance

Résumé du poste

Prime Intellect, Inc. is building open frontier AI and a full-stack platform for post-training at frontier scale. The Applied Research role focuses on RL systems, tool use by agents, and long-horizon problem solving across environments, harnesses, and evaluations.

You will collaborate with application teams and external users, delivering research that transfers across domains and contributes to open-source systems and publications.

Qualifications

• Hands-on RL training and scalable ML systems experience.
• Experience with agents, environments, evaluation, and inference/training infrastructure.
• Strong Python and ability to build reusable artifacts for researchers and engineers.
• Ability to own ambiguous problems and communicate with partners.

Responsabilités

• RL and post-training methods for tool-using, multi-agent, memory-augmented, and long-horizon systems.
• Reusable environments, harnesses, rewards, and evaluations.
• Experiments linking algorithm choices to training and inference behavior.
• Open-source systems and papers built from problems surfaced by application researchers and external users.

Connaissances

RL training

ML systems

Agent environments

Evaluation

Post-training

Python

Experimentation

Description du poste

Prime Intellect, Inc. is building open frontier AI and a full-stack platform for post-training at frontier scale. The Applied Research role focuses on RL systems, tool use by agents, and long-horizon problem solving across environments, harnesses, and evaluations.

You will collaborate with application teams and external users, delivering research that transfers across domains and contributes to open-source systems and publications.