Bio
Will Brown leads Applied Research at Prime Intellect and builds open research infrastructure to enable every company to train, deploy, and self-improve their own frontier agentic models. He holds a PhD in Computer Science from Columbia University.
Sessions (2)
Additional Speaker Details
Using publicly available information we constructed an analysis to help you get a feel for this speaker before deciding to attend their session.
Brown is the creator of the widely-used verifiers RL library and a leading public voice on agentic reinforcement learning; his sessions deliver a technical, infrastructure-grounded view of how to turn agent tasks into RL environments at scale, drawing directly from building Prime Intellect's open Environments Hub.
Speaking style
Deeply technicalBig-pictureBattle-tested
Recent talks (4)
RL Environments at ScaleAI Engineer Code Summit 2025 · Nov 2025
Scaling an Open Environments Ecosystem for Reinforcement LearningAI Engineer Code Summit 2025 · Nov 2025
Training Agentic ReasonersAI Engineer World's Fair 2025 · Jun 2025
How Prime Intellect Builds Scalable Infrastructure for Agentic RLRay Summit 2025 · 2025GitHub
@willccbb- willccbb/mlx_parallm★ 249Batched KV caching for fast parallel LLM inference on Apple Silicon via MLX
- PrimeIntellect-ai/verifiersorg★ 4,200Library for RL environments + evals; created by Will Brown, now Prime Intellect's core RL library
- genai-handbook/genai-handbook.github.ioorg★ 304The Generative AI Handbook he authored — a roadmap of generative-AI learning resources
Recent writing (2)
- Full-Stack Fine-Tuning for the Q Programming Language · paper · Aug 2025
- Reinforcing Multi-Turn Reasoning in LLM Agents via Turn-Level Reward Design · paper · May 2025
Podcasts & interviews (2)
- Multi-Turn RL for Multi-Hour Agents — with Will Brown, Prime Intellect · Latent Space: The AI Engineer Podcast · May 2025
- Building the GitHub for RL Environments: Prime Intellect's Will Brown & Johannes Hagemann · Training Data (Sequoia Capital)