NLAI Security Bootcamp, San Francisco
Global catastrophic risksAI safetyInformation securitySoftware engineering
Why this is on the board
Anyone who steals or manipulates a powerful AI model bypasses, in one go, all the safety measures its makers built into it. Few security professionals yet know how to protect such systems. This free week in San Francisco is not a job but a stepping stone for people with at least five years of security experience: your existing expertise becomes a rare combination that AI labs and governments are now looking for.
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 engage in lectures, demos, and red/blue team exercises covering the full AI attack surface. - Learn threat modelling, adversarial attacks, LLM security, infrastructure exploitation, model verification, and AI control across the modern stack. - Requires 5+ years hands-on security experience; no prior AI or ML ba…
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.