Building GPU-accelerated multi-agent apps with Google ADK and Gemma 4

Google Cloud Tech · Intermediate ·🤖 AI Agents & Automation ·2d ago
On this week’s livestream, join Chelsie Czop and @NVIDIA's Jay Rodge and learn how to build a GPU-accelerated sustainability intelligence app from scratch. You’ll learn how to orchestrate a team of specialist agents using the open-source Google Agent Development Kit (ADK), serve Gemma 4 efficiently on Cloud Run using NVIDIA RTX PRO 6000 GPUs, and connect them with Milvus for policy retrieval. Whether you are looking to deploy local models or scale production agentic workflows, this is the architecture blueprint you need. This livestream will air on Tuesday, May 12, 2026 at 9:00 A.M. PDT/12:00 P.M. EDT. Speakers: Chelsie Czop, Jay Rodge Products: Agent Development Kit, Gemma 4, Cloud Run
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related AI Lessons

Understanding Real-Time Customer Intent: The New Frontier for Retail AI Chatbots
Learn how retail AI chatbots can leverage real-time customer intent to drive sales and loyalty, and why it matters for modern retail
Medium · AI
Artificial Intelligence Is Not Replacing Humans - It’s Replacing Certain Behaviors
AI is replacing certain human behaviors, not humans themselves, and understanding this distinction is crucial for effective AI integration
Medium · AI
How I cut my LangChain agent's token costs by 93% with one import
Cut LangChain agent's token costs by 93% with a simple import and optimization technique
Dev.to · Mahika jadhav
5 Passive Income Streams Your AI Agent Can Run While You Sleep
Automate passive income streams with AI agents to earn money while you sleep, leveraging affiliate marketing, print-on-demand stores, and more
Dev.to AI
Up next
Introducing Interwhen: Steering reasoning agents with real-time verification
Microsoft Research
Watch →