Jailbreaking Lead

The role

FAR.AI is seeking a Jailbreaking Lead to own and lead the core technical engine of the red team, focusing on breaking the most heavily defended frontier models and setting the technical bar for vulnerability severity and generality.

What you'll do

• Develop universal and near-universal jailbreaks against frontier closed- and open-weight models
• Systematically dismantle defense-in-depth stacks
• Escalate initial vulnerabilities to expose their most severe form
• Own the technical bar for vulnerability severity and generality on every major engagement
• Invent new attack classes when existing techniques fail
• Monitor and rapidly incorporate state-of-the-art methods from the literature

What it takes

• Track record of finding non-obvious, high-severity vulnerabilities in frontier AI systems
• Deep technical craft with the judgment to know which vulnerabilities actually matter
• Experience with black-box optimization methods and multimodal attacks
• Experience with jailbreaking and deep understanding of large language model architectures
• Strong communication skills to make frontier labs and governments act on findings
• Track record in AI, adversarial ML, security, or another highly technical subject

What you'll bring

How we treat you

Health Insurance, Retirement, PTO, Paid Leave, WFH Stipend & Equipment, Catered Meals (Berkeley Office Only)

How to apply

Apply directly on FAR.AI's site. We link straight through — no resume parsing, no profile to fill out.

This listing is aggregated from a third-party source and its summary may be auto-generated, so details can be inaccurate or out of date. ForGood is not the employer and is not liable for the content — please verify everything on FAR.AI's official posting before applying.