About this role
Leads execution and evolution of offensive security activities focused on AI/ML systems, platforms, and integrations, owning the design, execution, and reporting of AI-focused red team operations targeting models, data pipelines, AI-enabled applications, and supporting infrastructure. Acts as a senior technical authority and program lead for AI red teaming, driving maturity through repeatable testing methodologies, automation, custom tooling, research, and mentoring.
Skills for this role
AI red teamingAdversarial testingThreat emulationLarge Language Models (LLMs)Vision modelsSpeech modelsDecision systemsModel deployment environmentsAPIsPluginsAgentsRAG pipelinesTraining pipelinesInference pipelinesData ingestionData labelingData governancePrompt injectionData poisoningModel inversionJailbreaksSupply chain risksCustom tooling developmentAutomationSecurity researchDetection engineeringAI governanceAdversary emulationMulti-stage attack chainsExploit development