SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 150,000 - 300,000 / annual
Prime Intellect is building the open superintelligence stack—infrastructure for frontier AI labs to conduct post-training at scale. The company has raised $150M from Founders Fund, Radical Ventures, NVIDIA, and prominent AI operators including Andrej Karpathy and leaders from OpenAI, Perplexity, Cognition, and others.
In this Applied Research role focused on reinforcement learning and ML systems, you will work on agentic RL for long-horizon reasoning, tool use, multi-agent coordination, failure recovery, and continuous improvement. Your work spans algorithms, environments, harnesses, reward and credit-assignment methods, evaluation, and scalable experimental systems, with the goal of creating methods that transfer across multiple application domains.
Key responsibilities include:
- Developing RL and post-training methods for tool-using, multi-agent, memory-augmented, and long-horizon systems
- Building reusable environments, harnesses, reward signals, and evaluations
- Running post-training experiments against real baselines and determining whether gains come from model, data, harness, inference, or infrastructure
- Designing agentic judges and credit-assignment methods that inspect complete trajectories and assign learning signals beyond final scores
- Making multi-agent and long-horizon environments train reliably at scale while maintaining debuggable traces and comparable baselines
- Detecting reward hacking, harness behavior, data leakage, and infrastructure artifacts, then redesigning loops to ensure results survive scrutiny
- Creating open-source systems and papers from problems surfaced by application researchers and external users
- Working directly with customers, users, and research partners while maintaining a substantive research agenda
Recent Prime work includes verifiers v1, an algorithms layer for prime-rl, multi-agent training systems, Prime Agent, and RL systems tested at trillion-parameter scale.
REQUIREMENTS:
- Hands-on experience with RL training, scalable ML systems, agent environments, evaluation, inference/training infrastructure, or research crossing methods and systems
- Demonstrated ability 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 willingness to change direction based on evidence
- Strong Python proficiency and ability to build artifacts that other researchers and engineers can run, inspect, and extend
- Comfort owning ambiguous problems and keeping partners and teammates informed as you resolve them
- Evidence of exceptional work through publications, open-source systems, benchmarks, or shipped products; ability to articulate what failed and how evidence changed your approach
