Step into the front lines of artificial intelligence with Large Language Models, the technology driving today’s smartest tools and applications.

If you want to move beyond basic API calls and truly understand how LLMs work, adapt, and process information under the hood, this course provides the technical bridge from foundational NLP to cutting-edge AI engineering.

Learn by building, not just reading

Designed for engineers and data enthusiasts ready to dive deep, this course skips high-level fluff and drops you directly into code. You’ll work through short, focused modules using industry-standard tools, vector databases, and modern frameworks.

Starting with NLP foundations, you’ll work with tokenisation, embeddings, classifiers, and language modelling before progressing to neural networks and modern transformer architectures.

Build and fine-tune modern transformers

Build key transformer components from scratch, including Rotary Position Embeddings (RoPE) and Llama-style layers, before applying prompt engineering, Parameter-Efficient Fine-Tuning (PEFT), and LoRA to adapt pre-trained models.

Construct RAG and multimodal AI applications

Build end-to-end Retrieval-Augmented Generation (RAG) pipelines using vector storage and knowledge-grounded semantic inference. Finally, create GenAnkiCards, combining LLM text generation with dynamic image and audio components and Anki integration.

By the end, you’ll be able to understand LLM internals, build transformer models, fine-tune efficiently, construct production RAG pipelines, and develop full-stack AI applications.