jobs

Software Engineer, Productivity - Inference Runtime

About the TeamWe’re hiring a Developer Productivity engineer to support OpenAI’s Inference Runtime teams. These teams own the systems responsible for serving models reliably, efficiently, and safely across Codex, ChatGPT, API, and internal

In inglese

Company

OpenAI

Location

San Francisco

Status

Open

Posted

2026-05-10T17:33:59.627+00:00

OpenAI is hiring a developer productivity engineer to support its Inference Runtime teams, which serve models across its products and research workloads. The role centers on deploy-gate tooling and validation infrastructure for inference engine images: canary and large-scale validation, CI hardening, reducing flaky failures, release and rollout automation, and triage tooling. It asks for experience with CI/CD, testing and release systems and comfort in Python-heavy distributed environments; C++ and prior inference experience are helpful but not required. The posting stresses that the work directly affects model launches.