Curated collection of professional AI courses, tutorials, and hands-on training from industry experts. Master LLMs, AI Agents, and advanced AI development.
This page features carefully curated training courses and resources for learning Large Language Models (LLMs) and AI Agent development. These courses range from beginner-friendly introductions to advanced implementation guides, taught by leading experts from Stanford, industry professionals, and AI practitioners.
All resources are external links to high-quality educational content.
A comprehensive introduction to Large Language Models covering foundational concepts, architectures, and how they work. Perfect for beginners looking to understand the technology powering modern AI applications like ChatGPT and Claude.
Start Course →Learn to build Large Language Models from the ground up. This course walks you through implementing transformers, attention mechanisms, and training pipelines. Gain deep understanding by building the technology yourself.
Start Course →Stanford University's comprehensive overview of Agentic AI systems. Learn about autonomous agents, multi-agent systems, and the future of AI from one of the world's leading institutions in AI research and education.
Start Course →Master the art of building AI agents and learn how to evaluate their performance. Covers agent architectures, tool use, planning strategies, and metrics for measuring agent effectiveness in real-world scenarios.
Start Course →Deep dive into building production-ready AI agents. Learn advanced techniques for creating reliable, efficient, and scalable autonomous systems. Covers error handling, multi-agent coordination, and deployment strategies.
Start Course →Learn to build AI agents using the Model Context Protocol (MCP). This course covers the MCP framework, its architecture, and how to leverage it for creating sophisticated agent systems with standardized communication.
Start Course →Comprehensive tutorial on implementing an AI agent from the ground up. Learn the core components, decision-making logic, memory systems, and tool integration by building everything yourself without relying on pre-built frameworks.
Start Course →Explore philosophical agents and advanced reasoning systems. This specialized course covers agents that can engage in complex reasoning, ethical decision-making, and philosophical discourse using advanced AI techniques.
Start Course →Comprehensive deep dive into Large Language Models covering advanced architectures, training techniques, optimization strategies, and the latest research developments. Perfect for those who want to master LLM technology at a deep level.
Watch Course →Master the Transformer architecture that powers modern LLMs. Learn about attention mechanisms, positional encoding, multi-head attention, and how these components work together to create powerful language models.
Watch Course →Complete neural networks course from scratch to advanced topics. Build your understanding step by step, starting with basic perceptrons and progressing to complex deep learning architectures. Includes practical implementations.
Start Series →Learn the complete lifecycle of GPT models from conception to deployment. Understand the training process, data preparation, model architecture decisions, and optimization techniques that create powerful language models.
Watch Course →Deep dive into Reinforcement Learning from Human Feedback (RLHF) and how GPT models learn to be helpful, harmless, and honest. Covers alignment techniques, reward modeling, and safety considerations.
Watch Course →Comprehensive guide to Retrieval-Augmented Generation (RAG) for engineers. Learn how to build RAG systems, integrate vector databases, optimize retrieval, and create production-ready applications that combine LLMs with external knowledge.
Watch Guide →Complete guide to fine-tuning LLMs for specific tasks and domains. Part 1 covers the fundamentals of fine-tuning, dataset preparation, hyperparameter selection, and evaluation metrics for custom models.
Watch Part 1 →Advanced fine-tuning techniques including parameter-efficient methods (LoRA, QLoRA), instruction tuning, few-shot learning optimization, and deploying fine-tuned models in production environments.
Watch Part 2 →Learn why the Model Context Protocol (MCP) is becoming essential for AI developers. Understand how MCP enables standardized communication between AI models and tools, making agent development more efficient and scalable.
Watch Now →Complete learning path from DeepLearning.AI covering Generative AI from foundations to advanced applications. Includes courses on prompt engineering, LangChain, vector databases, and building production GenAI systems.
Start Learning Path →Looking for more AI learning materials? Check out our other pages: