Courses
Video courses by the SOTAAZ team — streamed here on sotaaz, and published on Udemy.
Watch on sotaaz
Streamed here, with the notebooks and lecture scripts alongside.
All Courses Bundle
12 courses · 32h 28m · Every video course on sotaaz — lifetime access, one payment
Attention and Transformers from Scratch
From RNN Seq2Seq to Bahdanau and Luong attention to a full Transformer — built, trained and explained in PyTorch
DDPM and DDIM from Scratch
Derive and implement DDPM and fast DDIM sampling in PyTorch — from the paper to working code on MNIST
Latent Diffusion to SANA
Stable Diffusion, VAE and CFG, Diffusion Transformers, PixArt-α and SANA — implemented in PyTorch
Neural Network Quantization in PyTorch and ONNX
Number formats, quantization math, dynamic/static/QAT, ResNet and YOLO on ONNX Runtime — measured, not assumed
LLM Quantization and Compression
GPTQ, AWQ, bitsandbytes, GGUF, QLoRA, pruning and distillation — fit LLMs into the memory you have
GraphRAG Fundamentals
Why vector RAG fails, what a knowledge graph fixes, and how to index and query with Microsoft GraphRAG
GraphRAG in Production
Real documents, production indexing and cost, LLM-judge evaluation, multi-source provenance, and a GraphRAG agent
On-Device LLMs Model Preparation
Mobile hardware, compression theory, choosing a small model, and converting it with llama.cpp, MLC LLM and ONNX Runtime
On-Device Stable Diffusion Profiling and Export
Pipeline profiling, few-step generation with LCM and SDXL Turbo, ExecuTorch export with INT8 calibration, and Qualcomm QNN
Ship an LLM in an Android App
Kotlin with Compose and MediaPipe, React Native with llama.rn, hardware acceleration and NPU verification
Ship Stable Diffusion in an Android App
ONNX Runtime Mobile in Kotlin and React Native, cross-platform acceleration, an offline assistant capstone and a dual-track benchmark
RAG Evaluation and Trustworthy Agents
Ragas, LLM-as-a-judge, synthetic tests, guardrails, observability, retrieval diagnostics, agent eval, full audit
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 →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 →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 →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.
Be the First to Know
Subscribe to get notified when new courses launch.
Early subscribers get exclusive discounts.
Deep Dive Content
Production-ready implementations with real-world examples
Jupyter Notebooks
Runnable code you can experiment with immediately
Early Access
Subscribers get first access and exclusive pricing