A
Alignment Engineer, Frontier Red Team
FeaturedPythonLLM EvaluationRed TeamingSafety Research
About the role
Join Anthropic's Frontier Red Team to stress-test Claude for misuse risks, autonomy evals, and deceptive behavior. Fully remote, worldwide. You will design adversarial evaluations, build automated red-teaming pipelines, and publish safety research alongside the alignment science team.
Disclaimer: MMagic.ai connects talented people with AI companies around the world. While we work hard to feature quality opportunities, we don't independently verify employers, candidates, salaries, or hiring outcomes. We encourage you to research each opportunity and company before applying or making an offer.