This course provides a comprehensive overview of prompt tuning and prompt engineering techniques for optimizing large language model (LLM) performance. It covers the foundations of prompt engineering, including designing effective prompts and understanding core concepts like zero-shot and few-shot prompting. The course explores advanced techniques such as Chain-of-Thought prompting and Retrieval-Augmented Generation (RAG). Furthermore, it delves into prompt tuning methodologies, including soft prompts and parameter-efficient fine-tuning (PEFT), contrasting them with traditional fine-tuning approaches.