Software Engineer - Red Team
UK AI Security Institute · London, UK
Research instituteonsite
At a glance
Highlights
- Stress-test frontier AI systems to shape how powerful models are deployed.
- Share red-team findings directly with AI companies and allied governments.
- Probe misuse, misalignment and agent control risks across specialised sub-teams.
Ideal candidate
Software engineer who thrives partnering with researchers, turning ambiguous ideas into reliable systems and cares deeply about ensuring advanced AI is deployed safely.
Requirements
- Worked closely with research teams, building tools they want to use and automating workflows
- Good understanding of frontier AI capabilities, limitations, and risks
- Built infrastructure that works at scale with a high bar for security
- Experience with serving and training models
Lab profile
About UK AI Security Institute
UK government institute studying advanced AI risks and turning research into protective action.
Known for
- Alignment red-teaming
- Control red-teaming
- Misuse red-teaming
- Cyber and autonomous systems security
Key facts
- Based in the UK
- UK government-backed
- World's largest dedicated advanced AI risk team
Posted · Last seen