Senior AI Safety Researcher

Key Responsibilities: Lead the execution of red-teaming datasets, evaluation protocols, and technical risk reports, instituting QA checkpoints across various modalities Model bandwidth, allocate tasks among subject-matter experts, and maintain delivery velocity under tight deadlines Conduct rigorous technical reviews to ensure analytic outputs are defensible, reproducible, and aligned with dual-use containment standards

Required Qualifications: 2-4 years of experience in AI safety, red-teaming, CBRNE risk, or cyber threat intelligence Proven ability to manage complex technical projects and align specialized experts against demanding deadlines Sound technical judgment regarding dual-use risks and sensitive cyber vulnerabilities Clear communication skills for translating high-stakes risk architectures to engineering and executive leadership Advanced degree in a relevant field such as chemistry, biology, nuclear science, computer security, or AI (preferred)