This talk provides a practical introduction to edge AI for embedded systems developers, demonstrating how to leverage existing embedded knowledge to deploy machine learning on resource-constrained devices. Through a hands-on approach centered on real hardware, attendees will see the complete path from traditional embedded development to running neural networks on microcontrollers. Key Takeaways: • Understand the fundamental shift from rule-based to learned behavior in embedded systems • See a complete working example of TinyML deployment on constrained hardware • Learn one critical optimization technique (quantization) in practical terms • Know how to start with edge AI development