Guardian Platform Engineer — Real-Time Safety Systems

Owen Thomas B Corp; Greater London; Hybrid; GBP 100,000 - 165,000; Full time

Job summary

OpenAI in London is looking for a Software Engineer to design and build production systems that evaluate agent behavior, identify risk, and take action without adding friction for users. This hands-on role spans architecture, implementation, evaluation, and operations with ownership from exploration to production deployment.

You will work with alignment researchers and product/engineering teams to make agent safety a foundational capability across OpenAI, delivering reliable backend systems,

Responsibilities

• Design, build, and operate core components of Auto‑review and the broader Guardian platform, balancing safety, product utility, latency, and operational reliability.
• Build production systems that evaluate agent actions in real time, detect potentially harmful behavior, and support safe recovery or escalation paths.
• Improve how oversight systems understand user intent, environmental context, permissions, and relevant personalization signals while protecting privacy and avoiding unnecessary friction.
• Partner closely with alignment researchers to turn prototypes, evaluations, and new monitoring techniques into scalable product capabilities.
• Work across Product, Security, Infrastructure, and other engineering teams to integrate Guardian capabilities into agent experiences throughout OpenAI.
• Develop evaluations, adversarial tests, and monitoring to understand safety performance, false positives, latency, and user impact.
• Own projects end to end, contribute to technical direction and design reviews, and investigate failures to improve system behavior and reliability.

Job description

OpenAI in London is looking for a Software Engineer to design and build production systems that evaluate agent behavior, identify risk, and take action without adding friction for users. This hands-on role spans architecture, implementation, evaluation, and operations with ownership from exploration to production deployment.

You will work with alignment researchers and product/engineering teams to make agent safety a foundational capability across OpenAI, delivering reliable backend systems,