LLM course
Learn to build with large language models the way AI engineering teams do: reliable outputs, retrieval, evaluation, agents, fine-tuning and production. It is the LLM half of one program, taught in order.
Calling an LLM API takes ten lines of code. Building something people can rely on takes much more, and that is what AI-engineer job descriptions ask for:
Under all of it sits Module 5, where you build a small transformer yourself, so the model stops being a black box.
Every lesson has notes with worked examples, short video lessons, a hands-on lab with automatic checks, a practice path, a workbook and a timed exam. Each LLM module ends with a portfolio project, such as a bilingual policy assistant built with RAG, or a finance-operations agent that works through MCP tools with human approval.
Every module unlocks in order, after the one before it.
From your first line of Python to production LLM apps, RAG, agents, evals and fine-tuning. Reverse-engineered from 2026 AI-engineer job descriptions.
Still curious? Talk to us.
Yes. The program starts with Python for AI (Module 2) and the maths behind models (Module 3), and every module unlocks after the one before it, so you reach the LLM modules with the basics in place.
The labs work with hosted LLM APIs and open models, plus the tools AI teams use around them: vector search, evaluation suites, agent frameworks and the Model Context Protocol. The syllabus lists each lesson.
No. The LLM modules are part of the AI Engineering Program and unlock in order. One enrolment covers every module.
Yes. Lesson 1.1 is free: notes, a hands-on lab and a quiz, with no card.
AI vs ML vs DL vs GenAI: deep notes, a hands-on lab and a quiz. No card. No catch.