R
AI Security Researcher
AI SecurityAdversarial MLResearchPythonRed Teaming
About the role
Research adversarial attacks, red-teaming methods, and safeguards for production AI systems.
Responsibilities
Design security evaluations; publish findings; build product features.
Requirements
Background in AI safety, security, or adversarial ML; publications or practical experience.
Benefits
Remote-first, research budget, equity, benefits, high-impact mission.
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.