Software Engineer, RL Training Infra

Responsibilities

• Keep large-scale RL training runs moving by jumping into urgent engineering and infrastructure problems
• Debug issues across training systems, inference, orchestration, scaling, and distributed infrastructure
• Solve technical problems at the boundary between research and engineering, including scaling experiments and reducing latency
• Improve reliability and efficiency for RL training runs
• Help researchers develop infra-heavy integrations like multi-agent capabilities or memory
• Turn recurring operational issues into better tools, systems, processes, or abstractions
• Debug failures across model behavior, training data, RL systems, and evaluation infrastructure

Requirements

• Strong generalist engineer with experience in ML infrastructure
• Experience in RL, inference, scaling, training systems, or orchestration
• Ability to learn extremely quickly and operate across unfamiliar layers
• Strong debugging skills with high ownership and excellent communication
• Ability to work effectively in fast-moving environments with tight timelines

Preferred Qualifications

• Experience supporting large-scale model training or async RL systems
• Experience debugging distributed systems across GPUs, networking, or orchestration stacks
• Background in performance optimization or production-critical infrastructure
• Experience working directly with researchers or fast-moving model teams

About the Company

OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity.