AI Cyber Red Teamer

• In this role, you'll attack the cyber safeguards of frontier AI models to find vulnerabilities and help train them out.
• Design novel attack strategies against guardrails that prevent models from writing exploits.
• Document security failures and identify robustness gaps against prompt injection and other attacks.
• Test models' ability to assist with privilege escalation and real intrusions.
• Shape system cards and deployment decisions through your security research findings.

• In this role, you'll attack the cyber safeguards of frontier AI models to find vulnerabilities and help train them out.
• Design novel attack strategies against guardrails that prevent models from writing exploits.
• Document security failures and identify robustness gaps against prompt injection and other attacks.
• Test models' ability to assist with privilege escalation and real intrusions.
• Shape system cards and deployment decisions through your security research findings.

Trajectory Labs is a startup that builds RL environments for frontier AI labs to train robust, secure, and reliable models.