Research Engineer - RL Infrastructure

Role overview Build the systems foundation for large-scale reinforcement learning and distributed model training. The work spans infrastructure that helps models train efficiently, learn from real environments, and support post-training workflows such as tool use and agent tasks.

Responsibilities - Develop and optimize infrastructure for distributed training and large-scale RL workloads. - Improve the systems that connect compute, training environments, evaluations, and deployment. - Support reliable training across multi-node GPU clusters. - Collaborate with research and engineering teams to turn infrastructure needs into working systems.

Requirements - Strong software engineering experience relevant to machine learning systems or infrastructure. - Familiarity with distributed training or reinforcement learning workloads. - Ability to build and optimize systems used for demanding compute workloads.

Nice to have - Experience with multi-node GPU clusters and high-performance networking. - Contributions to open-source ML systems or infrastructure. - Interest in publishing technical work or writing about engineering insights.

Benefits and work setup - Full-time role with remote work or an in-person option in San Francisco. - Stated cash compensation range of $150,000–$350,000, including equity incentives. - Visa sponsorship and relocation assistance are available for international candidates. - Team off-sites, hackathons, conferences, and learning opportunities are offered.