Alignerr is seeking AI Red Team Testers to probe, challenge, and stress-test AI systems, uncover weaknesses before harm occurs. This isn't a traditional security role; it targets imaginative thinkers who love puzzles and lateral thinking.The position is remote and paid as an hourly contract. You'll design prompts and scenarios to reveal unsafe outputs, document failure modes with steps to reproduce, rate severity, and collaborate asynchronously with safety and research teams.
J-18808-Ljbffr
📌 Remote AI Safety Adversarial Tester (Roma)
🏢 Alignerr
📍 Roma
Candidati a questo annuncio
Mostra le tue capacità professionali all'azienda, compila il form e lascia un tocco personale nella lettera di presentazione, aiuterà il recruiter nella scelta del candidato.