Software Engineer, Model Deployment – ChatGPT Engineering

About the role

OpenAI is looking for a Software Engineer to build and evolve the platform that deploys, configures, and manages models for ChatGPT. You will work on large‑scale production systems that support the full model lifecycle, from orchestration to capacity planning.

Key responsibilities

• Design and develop deployment orchestration, model rollouts, and operational visibility tools.
• Automate incident detection, diagnosis, mitigation, and recovery workflows.
• Improve reliability, scalability, and efficiency of model deployments and supporting infrastructure.
• Build systems for capacity planning, resource allocation, and utilization monitoring.
• Partner with research, infrastructure, and product teams to deliver reusable platform capabilities.

Required profile

• 5+ years of software engineering experience building production infrastructure.
• Strong problem‑solving skills with a focus on turning complex operational challenges into reliable software.
• Excellent communication and collaboration across multiple engineering teams.
• Comfortable owning systems from design through production operation in fast‑moving environments.

Required skills

• Proficiency in Go, Python, C++, or Rust.
• Experience with deployment orchestration, configuration management, and infrastructure automation.
• Knowledge of highly available distributed systems and production reliability.
• Familiarity with observability, capacity planning, and incident response.