Episode

AI at the Edge is a different operating environment

Podcast
Practical AI
Published
Mar 25, 2026
Duration seconds
2819
Processing state
processed
Canonical source
https://share.transistor.fm/s/ea7694a9
Audio
https://pscrb.fm/rss/p/dts.podtrac.com/redirect.mp3/media.transistor.fm/ea7694a9/378817af.mp3
JSON
/v1/public/podcasts/practical-ai/episodes/ai-at-the-edge-is-a-different-operating-environment
Markdown
/podcast/practical-ai/ai-at-the-edge-is-a-different-operating-environment.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/practical-ai/episodes/ai-at-the-edge-is-a-different-operating-environment/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/practical-ai/ai-at-the-edge-is-a-different-operating-environment.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

What does “AI at the edge” really mean in 2026, and why does it matter now more than ever before? In this episode, we’re joined by Brandon Shibley, Edge AI Solutions Engineering Lead at Qualcomm’s Edge Impulse, to discuss the current state and future of Edge AI in 2026. We discuss Gen AI, Small Models, and Cascades of Models, along with real-world constraints like latency, power, and privacy. We also dive into the role of MLOps, evolving hardware, and how developers can start building practical edge AI systems today. Featuring: Brandon Shibley – LinkedIn Chris Benson – Website , LinkedIn , Bluesky , GitHub , X Daniel Whitenack – Website , GitHub , X Links: Read our Ultimate Guide to Edge AI Download your copy of O'Reilly's AI at the Edge Check out the Edge Impulse blog Sign-up for an expert led trial of Edge Impulse Upcoming Events: Register for upcoming webinars here !