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

🎯28 lectures · 3h 24m

Attention and Transformers from Scratch

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

3 lectures freeStart watching →
🌫️19 lectures · 2h 16m

DDPM and DDIM from Scratch

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

3 lectures freeStart watching →
🖼️23 lectures · 2h 37m

Latent Diffusion to SANA

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

3 lectures freeStart watching →
🔢41 lectures · 5h 39m

Neural Network Quantization in PyTorch and ONNX

Number formats, quantization math, dynamic/static/QAT, ResNet and YOLO on ONNX Runtime — measured, not assumed

3 lectures freeStart watching →
🗜️24 lectures · 3h 19m

LLM Quantization and Compression

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

3 lectures freeStart watching →
🕸️17 lectures · 1h 47m

GraphRAG Fundamentals

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

3 lectures freeStart watching →
🏭19 lectures · 2h 8m

GraphRAG in Production

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

3 lectures freeStart watching →
📱19 lectures · 2h 33m

On-Device LLMs Model Preparation

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

3 lectures freeStart watching →
🎨18 lectures · 2h 24m

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

3 lectures freeStart watching →
🤖14 lectures · 1h 42m

Ship an LLM in an Android App

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

3 lectures freeStart watching →
🖌️14 lectures · 1h 55m

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

3 lectures freeStart watching →
🧪18 lectures · 2h 45m

RAG Evaluation and Trustworthy Agents

Ragas, LLM-as-a-judge, synthetic tests, guardrails, observability, retrieval diagnostics, agent eval, full audit

3 lectures freeStart watching →
🧠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.

Coming Soon

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