Combining deep cybersecurity expertise with CBRNE knowledge, the full-time remote GenAI CBRNE Cybersecurity Expert will conduct adversarial testing of Generative AI systems against high-risk cyber threats, designing sophisticated attack scenarios and evaluating model vulnerabilities. Key responsibilities Execute rigorous adversarial red-teaming of Generative AI models to identify vulnerabilities and safeguard bypasses in cyber-CBRNE threat scenarios Design and implement adversarial prompts and attack scenarios that assess the effectiveness of model safeguards against sophisticated cyber-CBRNE requests Document findings, including failure modes and attack patterns, and provide actionable recommendations to enhance AI safety and model alignment Required qualifications Advanced degree in Cybersecurity, Computer Science, Engineering, Security Studies, CBRNE-related sciences, or a closely related technical field Deep understanding of cybersecurity concepts, adversarial techniques, and vulnerability analysis Strong knowledge of security considerations in Chemical, Biological, Radiological, Nuclear, and Explosive environments Demonstrated experience in red teaming, penetration testing, or comparable offensive-security methodologies Experience in adversarial prompt generation and evaluation of LLM safety controls