Red Teaming Jobs in San Francisco, CA

least one of the following areas: Cybersecurity, such as application security, penetration testing, vulnerability research, adversary simulation, or red-team

About the role Anthropic's Safeguards team is seeking a Red Team Engineer to help ensure the safety of our deployed AI systems

The role: We're hiring our founding team builder: the person who will assemble the most talent-dense team in the world

We're a small team punching far above our weight, working out of SF HQ and our new Toronto Hub.

Lead red team exercises in collaboration with stakeholders across the company to proactively identify vulnerabilities and stay ahead of emerging risks.

You’ll report to the Chief of Staff and sit on the operations team.

communication A clear point of view on AI/LLM security and hands-on experience defending relevant threats Bonus: prior experience with LLM red-teaming

This includes adversarial red-teaming for jailbreaks, PII leaks, and off-script behavior, plus production monitoring with live drift detection.

Experience coordinating vulnerability resolution across reporters, maintainers, security teams, and software releases.

Red-team end-to-end agentic systems to measure whether controls prevent data exfiltration, unsafe tool use, and other harmful outcomes.

Red teaming for agents, covering multi-step attacks, tool misuse and indirect prompt injection.

A team that spends more on inference and ships more is winning. A team that spends more and doesn't isn't.

Reducing per-sandbox memory overhead to raise density on each host Hardening the runtime against escape attempts found in internal red-team