PyTorch on the Edge: Amazon SageMaker x Qualcomm® AI Hub

Seamless cloud-to-edge AI development experience: Train on AWS, deploy with Qualcomm AI Hub

Curious how to get AI models onto real-world devices with performance to match your customers' needs? This workshop reveals how you can fine-tune PyTorch models in Amazon SageMaker, then optimize and test them directly on Qualcomm-powered hardware with no procurement of devices required.

Explore hands-on workflows for preparing your own data and models, validate performance on actual devices hosted in the cloud, and learn how to spot latency and reliability issues before launch. Discover new ways to accelerate your edge AI projects and network with peers during social hour after the workshop.

Learning Objectives

• Fine tune popular PyTorch models in Amazon SageMaker
• Use Qualcomm AI Hub to compile, profile, and optimize models for on-device deployment
• Rapidly scale testing using cloud hosted devices

Date/Time

Tuesday, October 21, 2025
12:00 - 7:00 PM PDT
Secure your spot, limited space available!

Location

InterContinental San Francisco
888 Howard Street
San Francisco, CA 94103

Who should attend?

ML Engineers, AI or Computer Vision Engineers, Data Scientists, Edge or Embedded Engineers, MLOps Engineers, Solutions Architects, and Product Managers for AI or ML

Speakers

• Karan Jain, Sr. WW Gen AI/ML Specialist, AWS
• Miron Perel, Principal Gen AI/ML Specialist, AWS
• Vinay Arora, Senior Gen AI Specialist Solution Architect, AWS
• Bastiaan Aarts, Principal Engineer, Qualcomm Technologies, Inc.
• Bhushan Sonawane, Staff Engineer Qualcomm Technologies, Inc.
• Shubham Patel, Senior Engineer, Qualcomm Technologies, Inc.
• Neel Kishan, Director, Product Management, Qualcomm Technologies, Inc. 

Agenda

Featured Partner