# #013: Prepping Your AI Model for the Wild: Building Edge AI Models That Work in the Real World

- Show: [Coredump Sessions](https://hardwarepodcasts.com/podcast/coredump-sessions)
- Published: 2025-07-23
- Length: 57m
- Episode: 14
- Page: https://hardwarepodcasts.com/podcast/coredump-sessions/2025-07-23-013-prepping-your-ai-model-for-the-wild-building-edge-ai-models-that-work-in-the
- Listen: https://podcasters.spotify.com/pod/show/memfault/episodes/013-Prepping-Your-AI-Model-for-the-Wild-Building-Edge-AI-Models-That-Work-in-the-Real-World-e35tsgq

## Summary

David Tischler and Alessandro Grande from Edge Impulse discuss the practical realities of deploying Edge AI models on constrained devices, emphasizing that customization and fine-tuning are the primary value propositions over raw model complexity. They explain how effective Edge AI requires a combination of traditional DSP pre-processing and ML models, and why hardware selection must balance compute power with software ecosystem usability. The conversation highlights the critical need for observability and OTA updates to monitor model drift and push fixes in the field, as models rarely work perfectly out of the box.

## Chapters

- [1:57](https://hardwarepodcasts.com/podcast/coredump-sessions/2025-07-23-013-prepping-your-ai-model-for-the-wild-building-edge-ai-models-that-work-in-the#t=117) Introduction: David Tischler and Alessandro Grande from Edge Impulse
- [5:19](https://hardwarepodcasts.com/podcast/coredump-sessions/2025-07-23-013-prepping-your-ai-model-for-the-wild-building-edge-ai-models-that-work-in-the#t=319) The Evolution of Edge AI: From Keyword Spotting to Industrial Use Cases
- [9:21](https://hardwarepodcasts.com/podcast/coredump-sessions/2025-07-23-013-prepping-your-ai-model-for-the-wild-building-edge-ai-models-that-work-in-the#t=561) Defining the Edge: Wearables, Factories, and the Value of Customization
- [26:13](https://hardwarepodcasts.com/podcast/coredump-sessions/2025-07-23-013-prepping-your-ai-model-for-the-wild-building-edge-ai-models-that-work-in-the#t=1573) Building the Software Stack: DSP, Impulses, and Democratizing AI for Embedded Engineers
- [34:17](https://hardwarepodcasts.com/podcast/coredump-sessions/2025-07-23-013-prepping-your-ai-model-for-the-wild-building-edge-ai-models-that-work-in-the#t=2057) Hardware Selection: MCUs, NPUs, and the Importance of Software Ecosystems
- [45:42](https://hardwarepodcasts.com/podcast/coredump-sessions/2025-07-23-013-prepping-your-ai-model-for-the-wild-building-edge-ai-models-that-work-in-the#t=2742) Observability and OTA Updates: Monitoring Model Drift and Field Performance
- [52:27](https://hardwarepodcasts.com/podcast/coredump-sessions/2025-07-23-013-prepping-your-ai-model-for-the-wild-building-edge-ai-models-that-work-in-the#t=3147) Audience Q&A: Fine-Tuning, TinyML, and Future Applications

## Topics

- [AI & machine learning](https://hardwarepodcasts.com/topic/ai-and-machine-learning)
- [Microcontrollers & dev platforms](https://hardwarepodcasts.com/topic/microcontrollers-and-platforms)
- [Connected products & IoT](https://hardwarepodcasts.com/topic/connected-products-and-iot)
- [Embedded firmware](https://hardwarepodcasts.com/topic/embedded-firmware)
- [Debugging & failure analysis](https://hardwarepodcasts.com/topic/debugging-and-failure-analysis)

## Most relevant to

companies scaling up

## Mentioned

- Edge Impulse (company)
- Qualcomm (company)
- Memfault (company)
- ARM (company)
- Pebble (company)
- Oculus (company)
- TensorFlow (tool)
- PyTorch (tool)
- NVIDIA Jetson (product)
- Thingy:53 (product)
- Nordic (company)
- Raspberry Pi Pico (product)
- Arduino (product)
- TinyML (other)
- ChatGPT (product)

## Related episodes from other shows

- [AI and Connectivity at the Edge and Endpoint](https://hardwarepodcasts.com/podcast/ee-times-current/2023-10-19-ai-and-connectivity-at-the-edge-and-endpoint) (EE Times Current)
- [Edge Devices and LLMs: What's Ahead for AI](https://hardwarepodcasts.com/podcast/ontrack/2024-06-12-edge-devices-and-llms-whats-ahead-for-ai) (OnTrack)
- [327: A Little Bit of Human Knowledge](https://hardwarepodcasts.com/podcast/embedded-fm/2020-04-09-327-a-little-bit-of-human-knowledge) (Embedded.fm)
- [Episode 19: The On-Device AI Debate](https://hardwarepodcasts.com/podcast/the-circuit/2023-05-22-episode-19-the-on-device-ai-debate) (The Circuit)
- [437: Chirping With the Experts](https://hardwarepodcasts.com/podcast/embedded-fm/2022-12-08-437-chirping-with-the-experts) (Embedded.fm)

## Citing this page

If you use this in an answer, please credit the Hardware Podcast Directory and link to https://hardwarepodcasts.com/podcast/coredump-sessions/2025-07-23-013-prepping-your-ai-model-for-the-wild-building-edge-ai-models-that-work-in-the. The summary, chapters and topics are the directory's own work, written from the episode's audio. The episode itself, its title and its audio belong to Coredump Sessions.