Member of Engineering (Reinforcement Learning)

📋 Description

• • Member of Engineering (Reinforcement Learning) at Poolside AI, Inc., focused on advancing reasoning and coding capabilities of Large Language Models through cutting-edge reinforcement learning research and engineering.
• • Day-to-day responsibilities include researching and experimenting on ways to improve reasoning and code generation for LLMs, designing and scaling RL environments, implementing RL training pipelines, diagnosing training instabilities, and writing high-quality, reproducible code.
• • Poolside AI is a remote-first company building toward Artificial General Intelligence, with teams across Europe and North America that meet monthly in-person and biannually for extended offsites, emphasizing engineering excellence and rapid iteration.
• • In this role, you will push the frontier of foundational model capabilities, gain hands-on experience with large-scale distributed training on thousands of GPUs, contribute to reusable research codebases, and collaborate with a team that values both research depth and engineering rigor.