Build practical skills in fine-tuning, AI agents, and multimodal Large Language Model (LLM) development to create intelligent AI applications. This course is designed for learners who want to move beyond basic prompt engineering and gain hands-on experience with model customization, automated tool usage, and text-and-image AI workflows.

You’ll learn to evaluate when prompt engineering or fine-tuning is the right approach, prepare JSONL training datasets, and fine-tune LLMs for consistent, domain-specific responses. You’ll then develop AI agents using structured functions, enabling them to automatically select and invoke appropriate tools to complete user requests and predefined operations. Finally, you’ll explore multimodal LLM applications by working with text and image inputs and developing an image captioning application that generates natural-language descriptions from visual content. By the end of the course, you’ll be able to evaluate model customization strategies, train customized LLMs, build AI agents with automatic tool selection, and develop multimodal AI applications. The course uniquely connects fine-tuning, agent development, and multimodal AI through practical implementation, giving you an applied path from model customization to intelligent AI applications.