AI Safety Red Team Tester — Remote Contract

Alignerr is seeking AI Red Team Testers to systematically probe cutting-edge AI systems, uncover blind spots, and report clearly on failure modes. This remote, hourly contract offers flexible scheduling and the chance to influence safety research across models.

No cybersecurity background required; a curious mind and strong writing are what matter. You will design prompts, test responses, document outcomes, and collaborate asynchronously with researchers to improve model behavior.