About the role
You will lead RateAI's adversarial red team, designing and running campaigns that stress AI systems the way a real, motivated attacker would. Your findings feed directly into pillar scores for Guardrail Resistance and Adversarial Robustness.
What you'll do
- Design jailbreak, prompt-injection, and multi-agent attack campaigns
- Lead structured red-team engagements against customer systems
- Document exploits and translate them into standing evaluation checks
- Stay ahead of emerging attack techniques across the AI landscape
What we're looking for
- Deep experience in offensive security, AI red-teaming, or adversarial ML
- Creativity and persistence in finding failure modes others miss
- Ability to communicate risk clearly to technical and non-technical audiences
Placeholder job description — replace with the final posting.
