Courses

Rebuild the measurements from the blog yourself. Every course is video plus the notebooks used on screen, and at least the first 3 lectures of each are free.

15 courses333 lectures37 hoursNotebooks includedLifetime access

Tracks:BUILDwrite it from scratch →HANDS-ONuse the real tools →SHIPrun it in production

Highlights

All courses

15 courses
Attention and Transformers from Scratch: what the course covers

Attention and Transformers from Scratch

From RNN Seq2Seq via Bahdanau and Luong attention to a full Transformer, built and trained in PyTorch

Build · 28 lectures · 3h 24m · first 3 free

$495 related posts
DDPM and DDIM from Scratch: what the course covers

DDPM and DDIM from Scratch

Derive and implement DDPM and fast DDIM sampling in PyTorch, from the paper to working code on MNIST

Build · 19 lectures · 2h 16m · first 3 free

$492 related posts
Latent Diffusion to SANA from Scratch: what the course covers

Latent Diffusion to SANA from Scratch

Stable Diffusion, VAE and CFG, Diffusion Transformers, PixArt-α and SANA, each implemented in PyTorch

Build · 23 lectures · 2h 37m · first 3 free

$493 related posts
Neural Network Quantization Hands-On: PyTorch and ONNX: what the course covers

Neural Network Quantization Hands-On: PyTorch and ONNX

Number formats, quantization math, dynamic/static/QAT, ResNet and YOLO on ONNX Runtime, all measured

Hands-On · 41 lectures · 5h 39m · first 3 free

$79
LLM Quantization and Compression Hands-On: what the course covers

LLM Quantization and Compression Hands-On

GPTQ, AWQ, bitsandbytes, GGUF, QLoRA, pruning and distillation: fit LLMs into the memory you have

Hands-On · 24 lectures · 3h 19m · first 3 free

$792 related posts
GraphRAG Hands-On: Knowledge Graphs for RAG: what the course covers

GraphRAG Hands-On: Knowledge Graphs for RAG

Why vector RAG fails, what a knowledge graph fixes, how to index and query with Microsoft GraphRAG

Hands-On · 17 lectures · 1h 47m · first 3 free

$39
GraphRAG in Production: what the course covers

GraphRAG in Production

Real documents, production indexing and cost, LLM-judge evaluation, provenance and a GraphRAG agent

Ship · 19 lectures · 2h 8m · first 3 free

$49
On-Device LLMs Hands-On: Prepare and Compress: what the course covers

On-Device LLMs Hands-On: Prepare and Compress

Compression theory, choosing a small model and converting it with llama.cpp, MLC LLM and ONNX Runtime

Hands-On · 19 lectures · 2h 33m · first 3 free

$491 related post
On-Device Stable Diffusion Hands-On: Profile and Export: what the course covers

On-Device Stable Diffusion Hands-On: Profile and Export

Pipeline profiling, few-step LCM and SDXL Turbo, ExecuTorch export with INT8 calibration, Qualcomm QNN

Hands-On · 18 lectures · 2h 24m · first 3 free

$49
Ship an LLM in an Android App: what the course covers

Ship an LLM in an Android App

Kotlin with Compose and MediaPipe, React Native with llama.rn, hardware acceleration and NPU verification

Ship · 14 lectures · 1h 42m · first 3 free

$39
Ship Stable Diffusion in an Android App: what the course covers

Ship Stable Diffusion in an Android App

ONNX Runtime Mobile in Kotlin and React Native, acceleration, an offline assistant capstone and a benchmark

Ship · 14 lectures · 1h 55m · first 3 free

$39
RAG Evaluation in Production: Trustworthy Agents: what the course covers

RAG Evaluation in Production: Trustworthy Agents

Score a RAG system with Ragas and LLM judges, diagnose its retrieval, evaluate the agent

Ship · 18 lectures · 2h 45m · first 3 free

$491 related post
Build a Jev-Style Decision Model from Scratch: what the course covers

Build a Jev-Style Decision Model from Scratch

An LLM that returns calibrated probabilities, not text: architecture, PyTorch build, training, serving

Build · 23 lectures · 1h 58m · all lectures free

$103 related posts
Claude Code Hands-On: CLAUDE.md, Hooks, Skills, Subagents: what the course covers

Claude Code Hands-On: CLAUDE.md, Hooks, Skills, Subagents

Drive Claude Code in a real repo: sessions, permissions, CLAUDE.md, hooks, skills and subagents, recorded live

Hands-On · 40 lectures · 1h 58m · first 3 free

$39
Claude Code in Production: MCP, Headless, Agent SDK: what the course covers

Claude Code in Production: MCP, Headless, Agent SDK

Connect tools with MCP, build your own server, run Claude Code headless in scripts and CI, and program it with the Agent SDK

Ship · 16 lectures · 42m · first 3 free

$29

What learners say

Real reviews from the instructor's courses, translated from Korean.

“Thanks to the well-structured curriculum and the instructor's clear explanations, I successfully transitioned into an LLMOps role.”
Learner review · LLM/LLMOps course (translated)
“I knew nothing about LLMs beyond prompts, but after finishing the course I applied it at work — and now I can pick up new techniques as they come out.”
Learner review · LLM course (translated)
“It covers things that are hard to learn from books or papers, delivered systematically, with hands-on labs built to make the concepts click. Highly recommended.”
Learner review · LLM course (translated)
“What I valued most: it goes beyond theory into prompt design and LLM applications you can actually use at work, all practice-driven.”
Learner review · LLM course (translated)
“RAG and prompting explained through the papers themselves. Picking good papers is hard, understanding them is harder — walking through them with hands-on practice made the concepts easy to grasp.”
Learner review · RAG/LLM course (translated)
“A solid introduction to Transformers — but a cut above any of the video lectures you can find on YouTube or elsewhere on the web. Thank you.”
Learner review · Transformer course (translated)
“I wandered all over trying to learn Diffusion, stumbled onto this course, and finally understood it completely.”
Learner review · Diffusion course (translated)

Bundles

Compared with buying each course on its own

AI Engineering Bundle · 13 courses

34h 25m · Every AI engineering course on sotaaz — lifetime access, one payment. One by one: $628.

Attention and Transformers from ScratchDDPM and DDIM from ScratchLatent Diffusion to SANA from ScratchNeural Network Quantization Hands-On: PyTorch and ONNXLLM Quantization and Compression Hands-OnGraphRAG Hands-On: Knowledge Graphs for RAGGraphRAG in ProductionOn-Device LLMs Hands-On: Prepare and CompressOn-Device Stable Diffusion Hands-On: Profile and ExportShip an LLM in an Android AppShip Stable Diffusion in an Android AppRAG Evaluation in Production: Trustworthy AgentsBuild a Jev-Style Decision Model from Scratch

Claude Code Bundle · 2 courses

2h 40m · Both Claude Code courses, from the daily loop to MCP, CI and the Agent SDK — lifetime access, one payment. One by one: $68.

Claude Code Hands-On: CLAUDE.md, Hooks, Skills, SubagentsClaude Code in Production: MCP, Headless, Agent SDK

Free code from the posts

The scripts and raw results behind the measurements. Free with an account.

For non-developers, on Udemy

🧠English

How ChatGPT Actually Works: LLM Principles Without Code

English edition — available now

How ChatGPT actually works, explained without code — for non-developers who want to understand what they are using.

View on Udemy →
🧠Korean

How ChatGPT Actually Works — Korean Edition

코드 없이 이해하는 ChatGPT 원리 — 비개발자를 위한 LLM 입문

The original Korean edition of the LLM fundamentals course.

View on Udemy →
✍️Korean

Prompt Design That Survives Model Updates — Practical AI, Principled

원리를 알고 써먹는 ChatGPT 실전 — 비개발자를 위한 프롬프트 설계와 AI 활용법

Prompt design grounded in principles, not templates — practical AI skills that survive model updates.

View on Udemy →
📊Waitlist · early-bird discount

AI in Practice for Data Analysts

분석가를 위한 AI 실무 — EDA·SQL·보고서 자동화와 검증

Where AI actually fits in an analyst's workflow — AI-assisted EDA, text-to-SQL you can trust, document Q&A, and verifying every number AI gives you. Measured error rates, not tips.

New courses by email

One weekly newsletter. New courses and the measurements behind them go in it.