Zum Inhalt springen
AI.info

jobs

Protection Scientist Engineer, Integrity

About the TeamThe Integrity team is responsible for the scaled systems that help identify and respond to bad actors and harm on OpenAI’s platforms. We protect users and the wider world by developing…

Auf Englisch

Company
OpenAI
Location
London, UK
Status
Open
Posted
2025-10-08 18:31 UTC

OpenAI's Integrity team in London seeks a protection scientist-engineer to build and maintain production systems that detect harmful use of its products. The role focuses on one area—scams, suicide and self-harm, or jailbreaks—and combines hands-on work on signals, classifiers and pipelines using SQL, Python, machine learning and language models with cross-functional strategy and launch protection. It asks for domain expertise, systems thinking and clear coordination. The job includes on-call escalations and possible review of sensitive or disturbing material.

Original job posting