Thread by @akshay_pachaar

10 GitHub repos that will set you up for a career in AI engineering (100% free):

1️⃣ ML for Beginners by Microsoft

A 12-week project-based curriculum that teaches classical ML using real-world datasets using Scikit-learn.

Includes quizzes, R/Python lessons, and hands-on projects. Some of the lessons are available as short-form videos.

Check this👇

2️⃣ AI for Beginners by Microsoft

This repo covers neural networks, NLP, CV, transformers, ethics & more. There are hands-on labs in PyTorch & TensorFlow using jupyter notebooks.

Beginner-friendly, project-based, and full of real-world applications.

Check this 👇

3️⃣ Neural Networks: Zero to Hero

Now that you’ve grasped the foundations of AI/ML, it’s time to dive deeper.

This repo by Andrej Karpathy is a hands-on course that builds modern deep learning systems from scratch, including GPTs.

Check this 👇

4️⃣ DL Paper Implementations

So far, you have learned the fundamentals of AI, ML, and DL. Now study how the best architectures work.

This repo covers well-documented PyTorch implementations of 60+ research papers on Transformers, GANs, Diffusion models, etc.

Check this👇

5️⃣ Made With ML

You’ve covered ML and neural nets. Now it’s time to learn how to go from notebooks to production.

Made With ML teaches you how to design, develop, deploy, and iterate on real-world ML systems using MLOps, CI/CD, and best practices.

Check this 👇

6️⃣ Hands-on LLMs

- You've built neural nets.
- You've explored GPTs.
- You've studied LLMs from the inside.

Now it’s time to apply them. This is a visually rich repo that will teach you everything about LLMs like tokenization, fine-tuning, RAG, etc.

Check this👇

7️⃣ Advanced RAG Techniques

Hands-on LLMs will give you a good grasp of RAG systems. Now learn advanced RAG techniques.

This repo covers 30+ methods to make RAG systems faster, smarter, and more accurate, like HyDE, GraphRAG, Vision RAG, etc.

Check this 👇

8️⃣ AI Agents for Beginners by Microsoft

After diving into LLMs and mastering RAG, learn how to build AI agents.

This is a hands-on course that teaches you how to build autonomous AI agents using real frameworks like Semantic Kernel, AutoGen, and MCP.

Check this👇

9️⃣ Agents Towards Production

The above beginner course taught you what AI agents are. Now it's time to learn how to ship them.

This is a practical playbook for building GenAI agents covering memory, orchestration, deployment, security & more.

Check this 👇

🔟 AI Engineering Hub

To truly master LLMs, RAG, and AI agents, you need projects.

AI Engineering Hub covers 70+ real-world examples, tutorials, and agent applications you can actually build, adapt, and ship.

Check this 👇

Links:

- ML for Beginners: github.com/microsoft/ML-F…
- AI for Beginners: github.com/microsoft/AI-F…
- NN Zero to Hero: github.com/karpathy/nn-ze…
- Paper implementations: github.com/labmlai
- Made with ML: github.com/GokuMohandas/M…
- Hands-on LLMs: github.com/HandsOnLLM
- Advanced RAG techniques: github.com/NirDiamant
- Agents for Beginners: github.com/microsoft/ai-a…
- Agents towards production: github.com/NirDiamant
- AI Engg. Hub: github.com/patchy631/ai-e…

Note: This roadmap moves toward LLMs, NLP, and AI agents after Made With ML, but don’t overlook CV and RL. They're equally powerful paths for AI engineers to explore.

If you found it insightful, reshare with your network.

Find me → @akshay_pachaar ✔️
For more insights and tutorials on LLMs, AI Agents, and Machine Learning!