Hands-on Workshop: AI Accelerated - Google Cloud + NVIDIA GPUs

Learn Hands-on from direct NVIDIA and Google Cloud

Important Note: A successful registration for this event will be a two step process as below. Meetup event is only a broadcast at this time and doesn't guarantee a seat to attend the workshop.

Step 1: Registration using the form https://rsvp.withgoogle.com/events/serving_open_models
Step 2: Confirmation of seat from Google Event team

This is a hands-on workshop with very limited seats delivered by NVIDIA and Google at the Google Toronto Office.

# Serving Open Models on Google Cloud Run and GKE

Join NVIDIA and Google Cloud for a hands-on workshop l focused on the cutting edge of enterprise AI, led by NVIDIA Developer Relations Manager Dimitri Maltezakis, and Google Cloud Go-To-Market lead Adam Lord —this session will take you from theory to live deployment.
In this workshop, you will:
Explore AI Infrastructure: Understand how deep integrations between Google Cloud and NVIDIA GPUs (like the RTX PRO 6000) are accelerating AI and data science workloads. Master NVIDIA NIM & Nemotron: Learn about the highly efficient Nemotron 3 family of open models (featuring up to a 1-million-token context length) and how to easily deploy them using NVIDIA NIM microservices. Deploy at Scale: Get hands-on experience deploying optimized large language models using serverless GPUs on Google Cloud Run and Google Kubernetes Engine (GKE).

Register NOW to secure your spot.
https://rsvp.withgoogle.com/events/serving_open_models

## Agenda

• 12:00 PM - 1:00 PM EDT
  Registration & Lunch
• 1:00 PM - 3:00 PM EDT
  Hands On Lab: Open Models on Cloud Run and GKE
• 3:00 PM - 5:00 PM EDT
  Networking Reception

##### WHAT TO BRING

• Please bring your laptop.

##### Why Attend

• Get Hands-on Experience: Complete a guided lab to deploy NVIDIA NIM on Cloud Run using serverless GPUs.
• Explore NVIDIA Open Models: Discover the NVIDIA Nemotron 3 family of models (including Nano, Super, and Ultra) and how they span capabilities across reasoning, vision, retrieval, safety, and speech.
• Optimize Your GPU ROI: Learn how to right-size GPU capacity and tailor compute resources using fractional G4 VMs powered by NVIDIA vGPU technology.
• Scale and Secure AI Workloads: Understand how to deploy and scale models in multi-node GKE environments using NVIDIA Dynamo, and how confidential G4 VMs help safeguard prompts, models, and data.
• Discover Cutting-Edge Integrations: Hear the latest on the Google Cloud and NVIDIA partnership, including NeMo Retriever on GKE, RAPIDS on Dataproc, and Gemini on NVIDIA for Regulated and Sovereign AI.

##### Who Should Attend

• AI/ML Developers and Data Scientists
• Cloud Architects and Platform Engineers
• DevOps and Infrastructure Professionals