Security Researcher: Offensive AI Agents & Enterprise Security

Antigen; San Francisco (CA); On-site; USD 140,000 - 210,000; Full time

Job summary

Antigen in San Francisco is seeking a security researcher to join our full-time team. You will be an expert-in-the-loop, deploying our agent tCell in complex systems, identifying breakdowns, and guiding the research team to improve capability.

You should be a strong offensive security practitioner with curiosity about how AI agents behave under adversarial conditions, and you will collaborate across security and engineering to advance enterprise-grade cyber defense.

Qualifications

• Strong offensive security practitioner with curiosity about AI agents in adversarial settings.
• Experience deploying and testing agents in enterprise environments.
• Ability to observe, document, and report failures to researchers.

Responsibilities

• Deploy tCell against complex systems and observe attack chains.
• Identify breakdowns and gaps in agent behavior.
• Collaborate with research team to turn findings into improvements.

Skills

Offensive security

Security research

AI/Agent systems

Job description

Antigen in San Francisco is seeking a security researcher to join our full-time team. You will be an expert-in-the-loop, deploying our agent tCell in complex systems, identifying breakdowns, and guiding the research team to improve capability.

You should be a strong offensive security practitioner with curiosity about how AI agents behave under adversarial conditions, and you will collaborate across security and engineering to advance enterprise-grade cyber defense.