Software Engineer, RL Training Infra

What this role involves

OpenAI is hiring a Software Engineer for RL Training Infrastructure to support large-scale reinforcement learning training runs. The role involves debugging and optimizing training systems, inference, and distributed infrastructure. The ideal candidate is a strong generalist engineer with experience in ML infrastructure and a focus on reliability and scalability.

Skills this posting asks for

• rl training
• inference
• orchestration
• scaling
• distributed infrastructure
• debugging
• multi-agent systems
• memory systems
• function calling
• factuality
• model behavior
• training data
• rl systems
• evaluation infrastructure
• serving systems
• agent harnesses
• gpus
• networking
• performance optimization
• large scale model training
• async rl systems
• high throughput ml infrastructure

From the employer’s posting

About the Team The Post-Training Frontiers team creates the frontier agents OpenAI ships to the world. We do the reinforcement learning training for the agentic models we ship in Codex, ChatGPT, and the API (from o1 to 5.5). Our role consists of (1) shepherding all integrations that should go int…