About the job
Poolside is committed to building Artificial General Intelligence within this decade. The company emphasizes rapid innovation, applied research, and large-scale deployment. By increasing the scale and capability of its models, Poolside aims to create economic value while focusing on user and customer success. The broader vision is to make AI central to meaningful work and scientific progress.
The team works remotely across Europe and North America, meeting in person for three days each month and gathering for longer offsites twice a year. Researchers and engineers collaborate closely, sharing responsibility for building high-quality systems. Strong engineering practices support fast development and amplify results.
Role overview
The Reinforcement Learning Engineer role focuses on advancing the reasoning and coding abilities of Large Language Models using reinforcement learning. This position combines research and hands-on engineering: designing new training algorithms, developing and scaling RL environments, and implementing solutions throughout Poolside’s technology stack. Substantial GPU resources are available to support these projects.
Mission
Expand the reasoning and coding capabilities of foundational models through reinforcement learning.
Key responsibilities
- Design and run experiments to improve reasoning and code generation in large language models. Oversee projects from initial idea through to integration.
- Stay current with the latest research in the field and contribute to ongoing research efforts.
This is a remote position open to candidates based in EMEA or on the East Coast of North America.
