Building and Deploying Generative AI Applications with Google Cloud Run

Watch a technical presentation where Google Cloud Product Manager Lisa Shen explores Cloud Run's serverless runtime platform and its powerful integration with generative AI applications. Learn how Cloud Run eliminates infrastructure management overhead while providing flexible container-based deployment options for modern workloads. Discover the platform's key resources including HTTP endpoint services and completion-focused jobs, alongside real-world implementation examples from L'Oreal and Ford. Follow along with a hands-on demonstration building a GenAI application that combines Cloud Run with Vertex AI, showcasing practical deployment workflows and architectural considerations. Gain insights into cost management strategies and scaling best practices for efficient application deployment. Recorded live at Google Cloud's Sunnyvale campus, this 32-minute session delivers essential knowledge for developers and architects interested in serverless computing and AI integration.