A project-driven guide to designing, training, and deploying artificial intelligence directly on embedded hardware, showing how to build intelligent, autonomous systems under real-world constraints. Embedded AI is a hands-on, hardware-first guide to building intelligent systems that run locally, in real time, on microcontrollers and single-board computers. Rather than focusing on theory or isolated case studies, the book emphasizes practical design decisions and the trade-offs engineers face when deploying AI on constrained devices. Readers begin with the foundations of embedded systems and machine learning, then learn how to collect, explore, and preprocess sensor data. The book places particular emphasis on exploratory data analysis, feature engineering, and data quality—areas that are critical to embedded machine learning but often overlooked. Using popular platforms such as Arduino, Raspberry Pi, STM32, and Seeed Studio boards, readers work through concrete projects including battery monitoring, hot-word detection, gesture recognition, noise classification, occupancy detection, and intelligent control systems. Industry-standard tools such as scikit-learn, TensorFlow Lite, and Edge Impulse are introduced only to the extent needed to support real projects. Advanced chapters address sensor fusion, power management, model compression, security, and privacy, helping readers understand how to build systems that are not just intelligent, but robust and deployable. The book concludes with a biologically inspired approach to embedded intelligence using the open-source Primal Layers framework, culminating in an embedded AI robot project.