This is your streamlined roadmap to learning AI and machine learning from scratch, for free. It starts with prerequisites, moves into machine learning fundamentals, and then engineering topics. This repo will be continually updated as I find great resources and create more guides.
Tip
While the whole learning path is free, some paid resources are included and marked with 💰. These paid resources further streamline your learning. I highly recommend them as they're from the best AI educators in the world.
This is an AI for Software Engineers resource. Subscribe to the newsletter to get more fundamental resources and technical deep dives in your inbox. If you'd like to support my work, you can subscribe there (paid or free—both help) and star this repository. Have a resource to add? See how to contribute.
Contents
Follow the resources in order down the page. Skip the topics you already understand well. You can skip to AI engineering section and come back to ML fundamentals later if AI engineering is your focus. I highly recommend going through the ML fundamentals section even if this is the case as it will give you a much deeper understanding of the topics in AI engineering.
Note
AI-assisted learning (experimental): You can load this repo in your favorite AI coding agent (Claude Code, Gemini CLI, Cursor, etc.) and have it walk you through the roadmap, find resources, and create exercises for you. This functionality is in beta and will be improved over time.
🚀 Enjoy the resources!
Programming
- CS50 by Harvard — Intro to programming
- Google's Python Class — Python basics
- NumPy Tutorial — Array operations
- Pandas Course by Kaggle — Data manipulation
Math
Tip
💰 This entire section can be streamlined via Tivadar Danka's Mathematics of Machine Learning book. It goes through all of the math topics in this section and more.
- Algebra by Khan Academy
- Linear Algebra by Khan Academy
- Probability by Harvard
- Derivatives by Khan Academy
- Backpropagation Visualization by Google
Tools
Ethics
- AI Ethics by Kaggle
Fundamentals
- What is Machine Learning? by Google — 20 min overview
- Machine Learning Crash Course by Google — Full course covering regression, classification, neural networks, embeddings, LLMs
- Spinning Up in RL by OpenAI — Reinforcement learning
- 💰 The RLHF Book by Nathan Lambert — Deep dive into reinforcement learning from human feedback
Tip
💰 I highly recommend reading Sebastian Raschka's book Machine Learning Q and AI to get a deeper understanding of fundamental machine learning and AI topics.
NLP & LLMs
- Intro to LLMs by Andrej Karpathy
- LLM Course by Maxime Labonne — Roadmaps, Colab notebooks, covers fundamentals to fine-tuning
- Learning to Reason with LLMs by OpenAI — How reasoning models work
Tip
💰 You can learn how to build your own GPT-3 level LLM step-by-step in Sebastian Raschka's book Build an LLM From Scratch.
Applications
- Computer Vision by Kaggle
- NLP Course by HuggingFace
- ML Explainability by Kaggle
- Knowledge Distillation by Dmitry Kozlov
- ML for Science by Molnar & Freiesleben
- ML for Games by HuggingFace
Hands-On
- Build a Recommendation System — Collaborative filtering with PyTorch by Logan Thorneloe
More coming soon to this section...
Building with LLMs
- Prompt Engineering Guide by Anthropic
- Building Effective Agents by Anthropic
- Testing and Evaluation by Anthropic
RAG & Infrastructure
- MCP Documentation — Connecting AI to external tools
- Building Agentic RAG by DeepLearning.AI
- Vector Databases Explained by Pinecone
Fine-Tuning & Local Models
- LoRA and PEFT by HuggingFace — Parameter-efficient fine-tuning
- How to Set Up Your Own Local Coding Model by Logan Thorneloe
Tip
💰 ML School by Santiago is a hands-on live cohort covering MLOps and many of the machine learning topics above.
- Made with ML by Goku Mohandas — Complete MLOps course from design to production
- ML Efficiency by MIT
- GPU Performance Engineering Resources by Wafer AI
- MLOps Community — Community for MLOps practitioners
Tip
💰 For deeper understanding, read Designing Machine Learning Systems by Chip Huyen — covers the architecture and trade-offs of production ML systems.
- 💰 Elements of Programming Interviews
- 💰 System Design Interview by Alex Xu
- Study Plan for ML Interviews by Khang Pham
| Resource | What You Get |
|---|---|
| Google Colab | Free T4/P100 GPUs |
| Kaggle Notebooks | 30 hours/week GPU |
| Lightning AI | 22 GPU hours free |
| Google Cloud | $300 free credits |
| Amazon SageMaker | Free tier |
| Paperspace Gradient | Free community tier |
Subscribe to AI for Software Engineers for more resources.
Support the creators! Buy the books, leave reviews, follow the authors.
Want to contribute? See CONTRIBUTING.md to add your resources to this roadmap.
Questions? Message me on X
