Red Team Engineer, Safeguards

Anthropic · San Francisco, CA · $320,000–$405,000 USD annually

Conducts adversarial testing of deployed AI products, including model jailbreaking and prompt-injection testing of agent workflows.

Independent aggregation of a publicly posted role. AI Compliance Index is not affiliated with, endorsed by, or recruiting for Anthropic. All applications happen on the employer's own site; listings may expire.