AI Engineering: Hands-on

A complete, hands-on to becoming a good AI Engineer.

This repository is designed to help you learn AI from first principles, build real neural networks, and understand modern LLM systems end-to-end. You'll progress through math, PyTorch, deep learning, transformers, RAG, and OCR — with clean, intuitive Jupyter notebooks guiding you at every step.

Whether you're a beginner or an engineer levelling up, this repo gives you the clarity, structure, and intuition needed to build real AI systems.

⭐ Star This Repo, If you learned something new, a star would be truly appreciated.

Repository Structure

1. Math Fundamentals

• Math functions, derivatives, vectors, and gradients
• Matrix operations and linear algebra
• Probability and statistics

2. PyTorch Basics

• Creating and manipulating tensors
• Matrix multiplication, transposing, and reshaping
• Indexing, slicing, and concatenating tensors
• Special tensor creation functions

3. Neural Networks

• Building neurons, layers, and networks from scratch
• Normalization techniques (RMSNorm)
• Activation functions
• Optimizers (Adam, Muon) and learning rate decay

4. Transformers

• Attention and self-attention mechanisms
• Multi-head attention
• Decoder-only transformer architecture

5. Retrieval-Augmented Generation (RAG)

• Building RAG pipelines end to end
• Indexing, retrieval, chunking strategies
• Integrations with embedding models and vector stores

6. Optical Character Recognition (OCR)

• OCR pipeline and utilities
• Preprocessing images and extracting text

Books

As someone who loves to read books, I have found the following books to be the best for learning AI. Some books PDF are added some are not added. Will add once I get the PDFs.

• SQL Cookbook by Anthony Molinaro
• AI Engineering by Chip Huyen
• Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow by Aurélien Géron
• Machine Learning With Python Cookbook by Max Kuznetsov
• Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville
• Pattern Recognition and Machine Learning by Christopher Bishop
• Neural Networks and Deep Learning by Michael Nielsen
• The Elements of Statistical Learning by Trevor Hastie, Robert Tibshirani, and Jerome Friedman
• Pattern Recognition and Machine Learning by Christopher Bishop

Learning Path

For a recommended step-by-step progression through the materials, see the Learning Path:

• Start_here/learning_path.md

Requirements

Install dependencies with:

pip install -r requirements.txt

Usage

Recommended workflow:

1. Open Jupyter in the project root:

   jupyter lab
   # or
   jupyter notebook

2. Work through notebooks in order:

   • 1.Math/
   • 2.PyTorch/
   • 3.Neural-Networks/
   • 4.Transformer/

3. Folder to run separately:

   • 5.RAG/
   • 6.OCR/

4. Resources

5. Basic ML Model Implementation (Supervised + Un-supervised + RL)

   • 1.Linear Regression
   • 2.Logistic Regression
   • 3.Decision Tree Model
   • 4.Naive Bayes Classification

Contributing

Contributions are welcome!

Please ensure:

• Notebooks are clean (Restart & Run All before committing)
• Existing structure & naming conventions are followed
• PRs are focused, readable, and documented
• In folders like RAG and OCR, please maintain the cleaned structure part
• If you want to add something new folders, make it proper structure way.

License

• This project is licensed under the MIT License. See LICENSE for details.

Connect with me