Principal Security Research Manager - Red Team
Core
Lead hands-on red-team operations and strategy to uncover critical weaknesses in advanced AI models, agentic systems, and AI-enabled products.
Role type
Principal Security Research Manager (Red Team)
Builds
High-fidelity attack campaigns, continuous adversarial testing suites, and automated threat reproduction tools for AI systems.
Domain
Artificial Intelligence Security / Adversarial Machine Learning
Deliverable
production ML models
Required skills
Adversarial machine learning, offensive security, attack automation, AI system testing, team leadership, technical strategy, risk assessment, engineering partnership, research methodology, tooling development
Preferred skills
Experience building new technical functions, hiring multidisciplinary talent, establishing security governance partnerships
Technologies
Large language models, agentic systems, agent frameworks, indirect prompt injection tools, AI-enabled security products
Responsibilities
Set attack strategy and severity bar for AI model weaknesses, lead hands-on red-team operations across models and training systems, design and operationalize automated attack suites, drive findings to verified remediation, track emerging AI attack techniques, evolve team methods and tooling
Seniority
Principal, hands-on IC with strategy & mentorship
