Design and implement evaluation methodologies for assessing AI model capabilities relevant to chemical weapons, explosives synthesis, and energetic materials.Design and implement evaluation methodologies for assessing AI model capabilities relevant to chemical weapons, explosives synthesis, and energetic materials, Develop and execute strategies to identify and mitigate potential C/E misuse in model outputs, Create C/E threat models, including precursor identification, synthesis routes, and weaponization techniques, Review and analyze traffic to identify potential policy violations related to C/E content, Collaborate with software engineers to develop and refine detection systems and automated enforcement tools for C/E threats, Conduct rapid response to escalations involving dangerous C/E queries, Collaborate across teams to establish safety benchmarks and develop appropriate model guardrails, Translate C/E domain knowledge into actionable safety requirements, Develop approaches to assess C/E model knowledge boundaries for dual-use chemical information, Monitor emerging threats in the C/E landscape to inform policy development.Ph.D. in Chemistry, Chemical Engineering, or a related field with focus on energetic materials, explosives, and/or chemical weapons, 5–8+ years of experience in chemical weapons and/or explosives defense, with deep expertise in energetic materials, chemical weapon agents, or related areas, Knowledge of high-yield explosives application to radiological dispersal devices (dirty bombs) and related radiological weapons, Track record of translating specialized technical knowledge into actionable safety policies or guidelines, Comfortable navigating ambiguity and developing solutions for novel safety challenges, Ability to work independently while maintaining strong collaboration with cross-functional teams including engineering, enforcement, and research, Thrive in a fast-paced environment where you balance rigorous scientific standards with rapid threat response, Passionate about preventing misuse of dangerous technical knowledge while enabling beneficial applications.