This book offers a comprehensive exploration of the intersection between Large Language Models (LLMs) and recommendation systems, serving as a practical guide for practitioners, researchers, and students in AI, natural language processing, and data science. It addresses the limitations of traditional recommendation techniques—such as their inability to fully understand nuanced language, reason dynamically over user preferences, or leverage multi-modal data—and demonstrates how LLMs can revolutionize personalized recommendations. By consolidating fragmented research and providing structured, hands-on tutorials, the book bridges the gap between cutting-edge research and real-world application, empowering readers to design and deploy next-generation recommender systems. Structured for progressive learning, the book covers foundational LLM concepts, the evolution from classic to LLM-powered recommendation systems, and advanced topics including end-to-end LLM recommenders, conversational agents, and multi-modal integration. Each chapter blends theoretical insights with practical coding exercises and real-world case studies, such as fashion recommendation and generative content creation. The final chapters discuss emerging challenges, including privacy, fairness, and future trends, offering a forward-looking roadmap for research and application. Readers with a basic understanding of machine learning and NLP will find this resource both accessible and invaluable for building effective, modern recommendation systems enhanced by LLMs.