handshake - AI Red Teamer, CBRNE (Remote)

• Design technically grounded adversarial prompts that test whether models provide meaningful uplift toward CBRNE threats • Evaluate model outputs for technical accuracy, assessing whether responses contain genuinely dangerous information versus superficial or publicly available knowledge • Probe dual-use knowledge boundaries, testing how models handle queries that blend legitimate scientific, medical, or industrial use cases with potential weapons applications • Test multi-step and multi-turn attack chains that simulate how a motivated actor might extract dangerous information incrementally • Score model responses against structured harm taxonomies and severity rubrics calibrated to real-world risk • Document findings with clear technical reasoning, including what a response gets right, what it gets wrong, and why the failure matters • Identify and articulate the difference between information that is freely available in open literature and information that constitutes genuine uplift beyond baseline • Contribute to the development and refinement of CBRNE-specific evaluation frameworks and threat models • Collaborate with other red teamers, AI researchers, and policy teams to translate findings into actionable model improvements • Stay current on evolving model capabilities, jailbreak techniques, and relevant developments in your domain • DESIRED CAPABILITIES • Graduate-level education or equivalent professional experience in a relevant CBRNE field (chemistry, biochemistry, microbiology, virology, nuclear physics, radiochemistry, materials science, munitions/ordnance, chemical engineering, or closely related disciplines) • Ability to evaluate the technical accuracy and real-world consequence of model outputs in your domain • Understanding of dual-use research concerns and the distinction between open-source knowledge and operationally significant uplift • Strong hands-on experience using multiple LLMs (ChatGPT, Claude, Gemini, open-source models, etc.) • Creative, adversarial problem-solving skills • Clear and precise written communication, including the ability to explain technical risk to non-specialist audiences • Strong ethical judgment and the ability to separate adversarial thinking from personal values • Self-directed, collaborative, and comfortable in feedback-heavy environments • You have spent years building deep expertise in a CBRNE-relevant field and want to apply that knowledge to AI safety • You can look at a model response about synthesis routes, enrichment processes, or dispersal mechanisms and immediately assess whether it crosses the line from textbook to actionable • You think in attack trees and threat models, not just individual prompts • You are comfortable working at the boundary between helpful scientific information and genuinely dangerous knowledge • You care about getting this right because you understand what the consequences of getting it wrong look like • CONTENT WARNING • This role involves regular and deliberate engagement with sensitive CBRNE-related content. You will craft and evaluate scenarios involving weapons of mass destruction, toxic industrial chemicals, biological agents, radiological and nuclear materials, and explosive devices. All work is conducted within a structured evaluation framework with strict ethical guidelines and operational security protocols. Candidates must be able to engage with this material professionally and sustainably.