jobs

Software Engineer, Model Deployment- ChatGPT Engineering

About the TeamChatGPT relies on a large and growing GPU fleet to serve inference workloads reliably and efficiently. We develop the systems and tools that make it possible to introduce new models, manage production deployments, respond to o

Company

OpenAI

Location

London, UK

Status

Open

Posted

2026-08-17T16:45:16.766+00:00

OpenAI's ChatGPT Engineering group is hiring a software engineer to build the platform that deploys and operates models across ChatGPT. The work covers deployment orchestration, configuration management, rollout tooling, operational automation, incident detection and recovery, plus capacity planning and resource allocation on a large GPU fleet. The posting asks for five or more years of production infrastructure experience, strong coding in Go, Python, C++, or Rust, and distributed-systems design skills. Model-serving or ML infrastructure interest is welcome; GPU or low-level hardware expertise is not required.