This course offers an in-depth exploration of the latest advancements and implementation practices for Large Language Models (LLMs) Development. Key topics include model inference and performance evaluation, data preprocessing for unstructured inputs, and document intelligence techniques. parts will gain deep knowledge about different mainstream models' inference details, experience about complex model data processing methodologies, and first-hand experience in deploying LLM agents across practical scenarios such as financial statement analysis, agent configuration, workflow orchestration, and the use of agentic methods in dynamic environments. Taught by leading academics and industry experts, the program combines foundational theory with applied learning to empower parts with the knowledge and skills to design, evaluate, and implement LLM solutions in operational settings.