From tokens to agents.
Master modern LLM engineering.
A hands-on course from tokenization to production agents, retrieval, fine-tuning, alignment, evaluation, and observability. Read, get quizzed, and build it yourself in 33 runnable notebooks.
3.5 Scaled dot-product attention
With Q, K, and V in hand, the entire mechanism is one formula:
Divide by √dₖ to keep softmax in its sensitive, well-behaved zone...
Quick check
Why divide by √dₖ specifically?
What you'll build
Every concept lands in a notebook you run yourself, not slides you watch.
Build a search engine from scratch
Tokenization, TF-IDF, and embeddings, see exactly how raw text becomes numbers a model can reason with, before you ever call an API.
Ship a real RAG pipeline
Parse, chunk, embed, retrieve, and re-rank your own documents, then measure whether it's actually grounded with Faithfulness and Answer Relevancy.
Build an agent with real tools
Wire an LLM into the reason-act-observe loop, connect it to MCP, and evaluate whether it actually completes multi-step tasks.
Deploy it like production, not a demo
Fine-tune with PEFT, align with DPO, then trace, monitor, and optimize inference, quantization, batching, routing, so it survives real traffic.
Why learn this now
Every product category is being rebuilt around language models, and the gap between "I called an API once" and "I can design, evaluate, and ship a reliable LLM system" is where the leverage is. The tools are moving fast, but the fundamentals underneath them, tokenization, attention, retrieval, alignment, evaluation, are stable enough to learn properly, once, and reason from for years.
$1T+
projected AI infrastructure spend by 2027
2×
engineers with LLM skills report faster promotion cycles
6 mo
how fast “state of the art” prompting advice goes stale
The full curriculum
16 modules · 61 lessons · 33 notebooks, grouped into 6 themes.
Getting Started
Foundations
Working with LLMs
Retrieval
Adapting models
Production systems
How the course works
01
Read
Short, focused lessons with the formulas rendered like a proper textbook, real diagrams, and worked examples, not a slide deck.
02
Get quizzed
Every module ends in a multiple-choice check with instant feedback, dynamic, like the compliance training that actually made you remember something.
03
Build it
Download the notebook, run it locally or in Colab, and implement the thing you just read about with your own hands.
One price. Everything included.
Monthly access
€4.99
per month, cancel anytime
- 16 modules, 61 lessons, full LaTeX-quality formulas and diagrams
- 33 hands-on Jupyter notebooks (download or run in Google Colab)
- Dynamic multiple-choice quizzes with instant feedback, every module
- 5 click-through interactive walkthroughs of key mechanisms
- Progress tracking across the whole course
- Full access while subscribed, cancel anytime
Secure checkout via Stripe. Questions? llmforge-support@agentmail.to
Frequently asked questions
Do I need a deep learning background?+
No. You need to be comfortable with Python and the command line. Every concept, including the math, is built up from first principles, with worked examples before any formula.
How long does the course take?+
Most people move through it in 4–8 weeks at a few hours a week. Lessons are short (2–15 minutes each); the notebooks are where the real time goes.
Do I need my own compute or API keys?+
A laptop is enough for most notebooks. A few labs call an LLM API, the setup guide inside the course walks through getting free-tier keys, and every notebook also runs on Google Colab's free tier.
Is this course kept up to date?+
The fundamentals (tokenization, attention, retrieval, evaluation, alignment) are stable and don't chase every model release. Where the field is moving fast, we say so explicitly and point you to the primary sources.
What if I want a refund?+
Cancel anytime from your account page, no future charges. If you want a refund for your most recent charge, email llmforge-support@agentmail.to within 14 days and you'll get one, no questions asked.
Do I get an invoice/receipt?+
Yes, Stripe emails a receipt automatically at checkout, and you can request a formatted invoice by replying to it.