Langley Langley is a reinforcement learning engineer with nine years of applied ML experience, focused on building high-skill, low-latency game AI systems for major studios and research labs. They have driven distributed RL training at scale—deploying Ray RLlib and PyTorch across 100+ nodes—and improved multi-agent performance through attention stabilization and game-theoretic algorithmic tweaks that delivered measurable win-rate gains. Langley’s work spans production integrations (Unity/C# control for agents) and research-grade innovations (self-play pipelines, fine-tuning for human-aligned actions), bridging engineering and scientific rigor. Comfortable communicating technical results to both stakeholders and non-technical audiences, they combine an MS in Computer Science with a background that blends academia and large studio practice, and have a recurring focus on making research robust under adversarial and real-time constraints.
Contributions:17 pushes, 1 branch, 3 comments in 1 year 2 months
pytorch
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.