AI Safety Red Teamer — Part Time

We need people who can think like attackers. You will methodically test AI models against a taxonomy of failure modes: harmful content generation, jailbreak susceptibility, PII leakage, bias amplification, and more. Each test is logged in a structured format that feeds into the safety team's tracking system. Successful exploits are prioritized for mitigation; unsuccessful attempts still provide valuable negative evidence.

The strongest red teamers combine technical curiosity with lateral thinking. You should be the kind of person who reads a policy document and immediately starts thinking about edge cases and loopholes. Familiarity with prompt engineering techniques, model architectures, and AI safety research literature is valuable. You should also be comfortable writing clear, detailed vulnerability reports.

Red team sessions are scheduled in 3-4 hour blocks. Most testers work 3-5 sessions per week. The work is mentally intense, so we encourage breaks between sessions. A weekly debrief with the safety team reviews top findings and updates attack priorities.