Member of Engineering (Reinforcement Learning Infrastructure)

📋 Description

• • Member of Engineering (Reinforcement Learning Infrastructure) at Poolside AI, Inc., focused on building and scaling infrastructure for reliable, efficient training of Large Language Models with Reinforcement Learning at the frontier.
• • Day-to-day responsibilities include staying current with LLM, RL, and code generation research; developing methods for high-throughput training and inference tuning; designing data control systems for RL pipelines; debugging infrastructure issues affecting learning dynamics; building observability tooling for system-level training regressions; constructing robust, scalable RL pipelines; optimizing performance across networking, memory, compute scheduling, and I/O; writing high-quality pragmatic code; and collaborating with the team on planning and technical discussions.
• • Poolside AI, Inc. is a remote-first company across Europe and North America, aiming to build Artificial General Intelligence by stacking advantages in applied research, engineering, infrastructure, and deployment at scale, with monthly in-person gatherings and biannual offsites.
• • The role offers the opportunity to work on cutting-edge AI infrastructure with access to thousands of GPUs, contribute to frontier LLM reasoning and coding abilities through RL, and develop deep expertise in distributed systems, performance optimization, and ML infrastructure at scale.