Applied Researcher - Agentic RL

Prime Intellect is building the open superintelligence stack, including the Lab platform that unifies compute, environments, evaluations, secure sandboxes, high-performance training, and deployment for post-training at frontier scale. This Applied Research role focuses on reinforcement learning for agents that reason over long horizons, use tools, coordinate with other agents, recover from failure, and improve from experience. The role is externally facing and combines a substantive research agenda with work alongside application teams, partners, and open-source users.

Responsibilities

Turn workflows into tasks, environments, evaluations, and reward signals; Run post-training experiments against real baselines and deploy what works; Determine whether gains come from the model, data, harness, inference, or infrastructure; Build agentic judges and credit-assignment methods that inspect complete trajectories and assign learning signal beyond one final score; Make multi-agent and long-horizon environments train reliably at scale while preserving debuggable traces and comparable baselines; Detect reward hacking, harness behavior, data leakage, or infrastructure artifacts and redesign the loop so results hold up; Own RL and post-training methods for tool-using, multi-agent, memory-augmented, and long-horizon systems; Build reusable environments, harnesses, rewards, and evaluations; Run experiments connecting algorithm choices to training and inference behavior; Produce open-source systems and papers built from problems surfaced by application researchers and external users; Work directly with customers, users, research partners, application teams, and open-source users

Requirements

Relevant experience in hands-on RL training, scalable ML systems, agent environments, evaluation, inference/training infrastructure, or research crossing methods and systems; Hands-on experience building and debugging model-training, post-training, agent, evaluation, or closely adjacent experimental loops; Strong experimental judgment: meaningful baselines, careful trace inspection, clear failure attribution, and a willingness to change direction when the evidence changes; Strong Python and the ability to build artifacts that other researchers and engineers can run, inspect, and extend; Comfort owning ambiguous problems and keeping partners and teammates current as you resolve them

Nice to have

Publications; open-source systems; benchmarks; shipped products

Benefits

Cash compensation range of $150-300k; Equity incentives; Flexible work (San Francisco, New York, London, or remote); Visa sponsorship and relocation support; Professional development budget; Team off-sites and conference attendance