AI Security Bootcamp, London
Why this is on the board
Whoever secures the most powerful AI models helps decide how likely they are to be stolen or misused. Yet few people combine years of security experience with knowledge of attacks aimed specifically at AI. This week teaches that combination to twenty specialists with at least seven years' experience, for a shortage AI labs and governments are already running into.
This board is in beta and this is our judgement. If you think we have it wrong, tell us. Give feedback · How we reason about it
About the role
A seven-day intensive bootcamp equipping security professionals with hands-on skills to secure frontier AI systems against emerging threats. - Complete pre-work on ML fundamentals, then attend immersive week covering threat modelling, adversarial attacks, LLM security, infrastructure, and AI control. - Build practical capability across the full AI attack surface: model vulnerabilities, supply chain attacks, agent security, and infrastructure exploitation. - Requires 7+ years hands-on security…
Not the right role? Get new ones every month
On the first Tuesday of every month: new jobs and programmes from this board, plus events in the next six weeks and the best of the EA Forum.
Want to understand this first?
Start with our free course: about 100 minutes in six short units, at your own pace, with no sign-up. To go further, apply for the EA Fellowship: five weeks of reading and discussion in a small group. Also free, but selective.