Jailbreaking Lead (Red Team)
F
FAR.AIAI Safety Research
Remote globallyFull-TimeLead
Salary170,000 - 250,000 USD per year
Apply NowOpens the employer's application page
Job Details
- Required Skills
- Cybersecurity
Requirements
- Personally developed universal or near-universal jailbreaks against at least one leading frontier model.
- Deep, hands-on jailbreaking experience against modern frontier models with layered defenses.
- Experience with black-box optimization methods, multimodal attacks, or agentic red-teaming.
- Deep understanding of LLM architectures, training processes, and failure modes.
- Strong track record in AI, adversarial ML, security, or other highly technical subjects.
- Demonstrated drive for mission-driven impact.
- Ability to thrive in rapidly evolving environments where techniques go obsolete fast.
- Communication skills for both technical and non-technical audiences including policymakers.
Responsibilities
- Lead jailbreaking on the highest-stakes engagements against frontier models.
- Systematically dismantle defense-in-depth stacks using novel and established attack techniques.
- Own the technical bar for vulnerability severity and generality.
- Invent new attack classes and shape the jailbreaking research agenda.
- Set the standard for rigor and creativity across the red team.
- Mentor ICs on attack craft and review red-teaming deliverables.
- Work directly with frontier labs and governments to implement mitigations.
- Contribute to public reports, benchmarks, and safety leaderboards.
View Full Description & ApplyYou'll be redirected to the employer's site
