Our team manages the testing infrastructure for Chrome’s AI features, while providing the tooling necessary to evaluate and optimize the underlying models. In this role, you will scale the testing and evaluation infrastructure for Gemini in Chrome. You will empower the team to build an autonomous, task-oriented agent directly within the browser. You will be responsible for developing the "source of truth" for the project—an end-to-end evaluation suite used to gate releases, benchmark model quality, and provide deep debugging insights for the broader engineering organization.

Triage product or system issues and debug/track/resolve by analyzing the sources of issues and the impact on hardware, network, or service operations and quality.

Gain a deep understanding of the AI testing and evaluation infrastructure for Chrome.

Apply debugging and creative thinking skills to find ways to address infrastructure problems in a new and expanding space.

Review code developed by other engineers and provide feedback to ensure best practices.