As an Agentic Safety and Ecosystem Architect, you will design for the safety and integrity of autonomous AI agents across the Android platform. Your focus is to bridge the gap between technical agent capabilities and the real-world safety of billions of users. You will be responsible for identifying and mitigating the harms that arise when AI agents interact with the OS and third-party apps—ranging from system-level instability to the creation of harmful synthetic media. By developing detection nets and enforcement frameworks, you will ensure that agentic features do not become vectors for abuse.

Develop the rules of engagement for autonomous agents on Android, ensuring that multi-step plans are audited for safety before execution.

Implement strict "least-privilege" models so agents cannot escalate system permissions or access sensitive user data without explicit, context-aware consent.

Partner with the Product team to build runtime monitoring that identifies "agentic drift," recursive loops, or adversarial attempts to hijack agent reasoning.

Create self-testing kits for the Android developer community to ensure that third-party agents are built with brakes and kill-switches.