> Markdown version of [/events/world-congress-2025/sessions/878-ai-at-the-edge-build](https://www.wearedevelopers.com/events/world-congress-2025/sessions/878-ai-at-the-edge-build). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# AI at the Edge: Build a Smarter IoT on Arm


- **Date:** Friday, Jul 11, 2025
- **Time:** 14:45–16:45 (120 min)
- **Room:** M3 (45 Seats)
- **Event:** World Congress 2025

## Description

The next wave of AI is happening at the edge – and you’re going to build it. In this workshop, you learn how to run powerful AI on ultra-constrained IoT devices using Arm Ethos-U NPUs, backed by the latest architecture and tools. Walk through real-world workflows to build AI-powered, energy-efficient systems, and preview the new Arm Ethos-U85 making light work of running a GenAI model on FPGA. Bring your laptop and get hands-on with model optimization and deployment using the MobileNet model on the virtualized Arm Corstone reference package, which simulates NPU hardware. By the end, you’ll have the skills (and the toolchain) to start creating intelligent edge AI solutions that deliver high performance without draining power. 

*All workshop attendees are required to bring their own laptop*

## Speaker

### [Annie Tallund](https://www.wearedevelopers.com/@annie-tallund)

Solutions Engineer at Arm


## Related talks at this congress

- [Mobile AI on Arm: AI Text and Audio Generation Entirely on Device ](https://www.wearedevelopers.com/events/world-congress-2025/sessions/572-mobile-ai-on-arm-ai) — Michael Hall
- [Mobile AI Just Got Faster: What’s Coming for Developers on Arm](https://www.wearedevelopers.com/events/world-congress-2025/sessions/602-mobile-ai-just-got) — Gian Marco Iodice
- [Scaling LLM Applications on Arm: Optimize for Performance and Cost in the Cloud](https://www.wearedevelopers.com/events/world-congress-2025/sessions/508-scaling-llm) — Avin Zarlez
- [From Model to Metal: An Open Source Stack for Accelerating Intelligence](https://www.wearedevelopers.com/events/world-congress-2025/sessions/832-from-model-to-metal) — Andrew Wafaa