Guardian Platform Engineer – AI Safety Systems

OpenAI, Inc.; Greater London; On-site; GBP 110,000 - 170,000; Full time

Job summary

OpenAI is seeking a Software Engineer to join the Guardian team in London. You will design, build, and operate core components of Auto-review and related safety systems, evaluating agent actions in real time to prevent harm and minimize user friction.

You will work with alignment researchers and cross-functional teams to translate research into scalable product capabilities, owning projects end to end and shaping technical direction.

Qualifications

• Experience building and shipping complex production software.
• Proven ability to own features end-to-end.
• Experience with AI agents or large language models in core products.

Responsibilities

• Design, build, and operate core components of Auto-review and the Guardian platform.
• Build production systems that evaluate agent actions in real time and support safe recovery.
• Improve understanding of user intent, context, permissions, and personalization signals while protecting privacy.
• Partner with alignment researchers to turn prototypes into scalable product capabilities.
• Work with Product, Security, and Infrastructure teams to integrate Guardian into OpenAI experiences.
• Develop evaluations, adversarial tests, and monitoring of safety performance and user impact.
• Own projects end to end, contribute to technical direction and design reviews.

Skills

Production software

Backend services

APIs

Infrastructure

AI agents

Research collaboration

Job description

OpenAI is seeking a Software Engineer to join the Guardian team in London. You will design, build, and operate core components of Auto-review and related safety systems, evaluating agent actions in real time to prevent harm and minimize user friction.

You will work with alignment researchers and cross-functional teams to translate research into scalable product capabilities, owning projects end to end and shaping technical direction.