Description
Handshake AI is hiring a CBRNE Red Teamer to evaluate whether AI models appropriately handle queries involving chemical, biological, radiological, nuclear, and explosive threats. The role designs adversarial prompts, assesses technical accuracy and real-world risk, tests multi-step attack chains, documents failures, and contributes to CBRNE-specific evaluation frameworks. Candidates need deep expertise in a CBRNE field, strong ethical judgment, and experience with multiple large language models; security clearance, threat-assessment, biosafety, regulatory, red-teaming, scripting, and AI-evaluation experience are preferred.
