Lead the team's strategy, research and direction to identify risks and threats with an evolving AI threat landscape. Translate insights into proactive mitigation goals to address novel abuse and attack vectors across product surfaces and capabilities.
Provide technical leadership to scope and drive comprehensive, transparent and scalable anti-abuse defenses for interconnected AI ecosystems.
Be the team's thought leader and engage with Engineering, Product, Policy and Legal to deploy scalable, and defensible mitigation processes for risks with Large Language Models (LLMs).
Lead adversarial simulations, proactive assessments, discovery programs to surface unknown attack vectors and risks of AI systems and next-generation capabilities. Architecting novel testing frameworks to expose, multi-stage vulnerabilities.
Direct rapid investigation, mitigation and response for high-severity AI abuse incidents, collaborating across product, research and policy teams.

Security Engineering Manager, Trust and Safety, Gemini and Labs

Job Description