Canyon Red Jobs in San Francisco, CA

About the Role As a Red Teamer focused on cyber, you will help answer two practical questions: What cyber capabilities can our

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

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

Contribute to the development of “best practices” guidelines for AI safety for OpenAI and across the industry Evaluate and design effective red-teaming

after 4 years, do something fun and new Available to US-based full-time employees Full coverage, no red

We're a team of founder types: enjoy autonomy, responsibility, the opportunity to learn, and no red tape. Just make it happen.

SWIFT/BIC, ABA, SEPA, BSB, IFSC, Japanese bank/branch codes) Identify and escalate business-email-compromise attempts and other payment-fraud red

Experience with modern red-teaming/jailbreaking techniques.

Experience with red-teaming or adversarial testing of AI systems.

Daybreak Red

injection, unsafe tool use, sensitive-data disclosure, policy violations, and hallucinated commitments Build adversarial evaluations, simulations, red-team

Familiarity with red-teaming or adversarial evaluation of post-trained models.