Own the product strategy and delivery schedule for Gemini models on Google Distributed Cloud across both connected and air-gapped environments, ensuring predictable release cadences and capability between public cloud and on-premises deployments. Partner with systems and runtime engineering teams to optimize critical inference metrics, such as Time to First Token, Time Per Output Token, and aggregate throughput, while integrating advanced capabilities into the local serving stack.
Serve as the primary product interface to AI research, model development, and safety teams across Google; establish shared release criteria, define model life-cycle and support policies, and oversee the integration of on-premises safety mechanisms, including intellectual property protections and model guardrails. Define and streamline end-to-end experiences for developers and system operators—spanning developer APIs, software development kits command-line tooling, identity and access management, local telemetry, and hardware capacity planning.
Job description provided by Google.
View the original posting
