ML/Research Engineer, Safeguards
San Francisco
Workplace: OnsiteFull timeUSD 350,000 - 500,000 annuallyFunction: Research & Scientific (R&D)Experience: 4+ yearsEducation: bachelorsSkills: ["Communication","Collaboration","Problem-solving"]Join the Safeguards ML team to build scalable systems that detect and mitigate AI misuse, develop defenses for agentic risks, and monitor harms across contexts. Work across the research-to-deployment pipeline, contribute to red-teaming and adversarial robustness efforts, and help ensure model safety and user wellbeing through scalable classifiers and evaluation environments.
Loading
Loading job details...
Preparing the role view and application actions.

