Edge AI refers to the use of AI techniques embedded in IoT endpoints, gateways and edge servers, that can process and store data close to where it’s generated. While predominantly focused on AI inference, more sophisticated systems may include a local training capability to provide in-situ optimization of the AI models. This is done by constantly monitoring AI models and autoscaling them to match demands. Edge AI systems can reduce latency and data transport consumption, improve local processing capabilities thus find usage in applications ranging from autonomous vehicles to streaming analytics.