AI Engineering Primer
A video-based, project-driven course bridging machine-learning theory and production AI-engineering practice, covering agentic systems, retrieval-augmented generation, orchestration, and fine-tuning large language models.
AI Engineering Primer is organized into three phases delivered as 46 video lectures with roughly 21 hours of total watch time and accompanying reading material and code labs. The first phase covers applied generative AI, agentic-system design patterns, retrieval-augmented generation, and building and orchestrating multi-agent workflows from scratch, including a bonus module on LangChain and LangGraph. Later phases move into pre-training and fine-tuning language models and the core deep-learning concepts behind building a language model.
Module one of the first phase, for example, covers the difference between agents and workflows, tool calling, the Model Context Protocol, context management, vector embeddings, human-in-the-loop intervention, and debugging with LangChain.
It is released under the MIT license.