NLHead of Red Teaming
SyntonyRemote
Why this is on the board
Whoever sets the testing method also determines which flaws testers find in AI systems before they reach users, and which they miss. In this role you set the standards for severity and retesting and deploy a whole network of testers, including in areas that are still little tested, such as AI that acts autonomously. What companies do with the findings is, however, decided by others.
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
Lead red teaming engagements for AI systems, managing methodology, a network of expert testers, and client workshops. - Run adversarial testing projects from scoping through reporting; set standards for test design, severity ratings, and retesting. - Recruit and coordinate the Trusted Red Team Network; match testers to projects and review finding quality. - Extend testing into vulnerable user harms, insider threats, agentic systems, and physical AI applications. - Requires 5+ years in red tea…
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.