Deployment path
Model export, runtime selection, profiling, and validation on target hardware.
Edge AI · Intermediate to advanced
Join the WaitlistEdge AI Deployment: Model to Device
Turn a trained model into a measurable, resource-aware inference service running on the hardware it was meant for.
October 2026 · Date to be confirmedDate
4 hoursDuration
OnlineFormat
The registration date will be announced to the waitlist first.
The workshop
Build with guidance, not another slide deck.
This upcoming session will cover the deployment work between a notebook model and a reliable on-device inference loop.
You'll leave with
Practical outcomes you can use immediately.
01Profile inference latency, memory, and throughput on target hardware.
02Choose quantization and runtime settings based on measured constraints.
03Build a repeatable packaging and validation path for edge models.
Session plan
Four focused hours.
Before you join
What you need
- Python familiarity
- A laptop with a working ML environment
- Interest in deploying to Raspberry Pi or Jetson
Included
What you get
- Reference deployment checklist
- Live walkthrough
- Workshop recording for registered attendees
Your facilitator
Analog Data
Embedded & Edge AI workshop seriesJoin the waitlist to receive the confirmed agenda, hardware requirements, and registration date.
Limited seats
Reserve your place.
The registration date will be announced to the waitlist first.
Join the workshop waitlist →