To advance AI safety and security, the full-time Security Research Engineer will develop validation techniques for confirmed vulnerabilities and advance patch methods, working remotely or onsite in various US locations. Key responsibilities Develop techniques that confirm vulnerabilities are real and reachable Advance approaches for generating and verifying safe fixes Define correctness, regression, and revalidation standards with reviewers Required qualifications Bachelor's degree (or equivalent experience) with 5+ years in security research or software engineering Hands-on experience in vulnerability research, fuzzing, program analysis, or secure development in C, C++, or Python Strong understanding of what constitutes a correct and safe fix, including regression and behavior preservation Comfort using AI-assisted tools for analysis and development