⭐ If this helped you, star it — it helps others find it too.
🚀 Start Learning · 📚 All Modules · 🏗️ Projects · 🤝 Contribute · 💬 Community
There are hundreds of LLM tutorials out there. Most are either:
- 🔴 Too shallow — "just call the API and you're done"
- 🔴 Too academic — dense math, no runnable code
- 🔴 Too opinionated — locked into one framework
- 🔴 Outdated — written in 2023 and never touched since
This curriculum is different. It's:
| ✅ | What you get |
|---|---|
| Beginner → Production | Start from zero ML knowledge. End with a deployed, monitored AI system. |
| Framework-agnostic | OpenAI, Anthropic, HuggingFace, open-weight models — you learn all of them. |
| Hands-on first | Every concept has code. Every phase has a capstone project you can put on your portfolio. |
| Community-maintained | Updated by practitioners, not just educators. PRs welcome. |
| Clearly leveled | Every module is tagged 🟢 Beginner · 🟡 Intermediate · 🔴 Advanced — no surprises. |
YOU ARE HERE
│
▼
┌──────────────────────────────────────────────────────────────┐
│ PHASE 0 · Foundations 🟢 No prerequisites │
│ What LLMs are, how transformers work, tokens & embeddings │
└───────────────────────────┬──────────────────────────────────┘
│
▼
┌──────────────────────────────────────────────────────────────┐
│ PHASE 1 · Prompting 🟢 Beginner │
│ Prompt engineering, CoT, few-shot, system prompts │
└───────────────────────────┬──────────────────────────────────┘
│
▼
┌──────────────────────────────────────────────────────────────┐
│ PHASE 2 · APIs & Integrations 🟢 Beginner │
│ Call LLMs from code. Build your first real app. │
└───────────┬───────────────┴───────────────┬──────────────────┘
│ │
▼ ▼
┌───────────────────────┐ ┌───────────────────────────┐
│ PHASE 3 · RAG 🟡 │ │ PHASE 4 · Fine-Tuning 🟡 │
│ Retrieval-Augmented │ │ LoRA, QLoRA, RLHF, │
│ Generation, vector │ │ dataset prep │
│ DBs, chunking │ └───────────┬───────────────┘
└───────────┬───────────┘ │
└───────────────┬───────────────┘
│
▼
┌──────────────────────────────────────────────────────────────┐
│ PHASE 5 · Agents 🟡 Intermediate │
│ Tool use, ReAct, memory, multi-agent systems │
└───────────────────────────┬──────────────────────────────────┘
│
▼
┌──────────────────────────────────────────────────────────────┐
│ PHASE 6 · Evaluation 🟡 Intermediate │
│ Evals, benchmarks, LLM-as-judge, eval pipelines │
└───────────────────────────┬──────────────────────────────────┘
│
▼
┌──────────────────────────────────────────────────────────────┐
│ PHASE 7 · Production 🔴 Advanced │
│ Deploy, scale, monitor, optimize, guardrails │
└───────────────────────────┬──────────────────────────────────┘
│
▼
┌──────────────────────────────────────────────────────────────┐
│ PHASE 8 · Advanced Topics 🔴 Advanced │
│ Train from scratch, multimodal, MoE, research papers │
└──────────────────────────────────────────────────────────────┘
Not sure where to begin? Pick your entry point:
Start → 00-foundations_what_are_llms.md
Start → 02-prompt_engineering.md
Start → 01-apis_quickstart.md
Start → 03-rag_pipeline.md
Start → 04-finetuning_lora.md
Start → 06-safety_guardrails.md
Legend: 📖 Guide · 🧪 Notebook · 💻 Code · 🏗️ Project · 🟢 Beginner · 🟡 Intermediate · 🔴 Advanced
No prerequisites. If you're brand new, start here.
| # | Module | Format | Est. Time |
|---|---|---|---|
| 0 | What Are LLMs? | 📖 | 20 min |
Learn to communicate with LLMs effectively. The highest ROI skill in this entire curriculum.
| # | Module | Format | Est. Time |
|---|---|---|---|
| 1 | Prompt Engineering Techniques | 📖 + examples | 1 hr |
Call LLMs from your code. Build your first real application.
| # | Module | Format | Est. Time |
|---|---|---|---|
| 2 | OpenAI API Quickstart | 📖 + 💻 | 1 hr |
Give your LLM a memory. Connect it to your own documents and data.
| # | Module | Format | Est. Time |
|---|---|---|---|
| 3 | Building a RAG Pipeline End-to-End | 📖 + 🧪 | 2 hr |
When prompting isn't enough — adapt a model to your exact task.
| # | Module | Format | Est. Time |
|---|---|---|---|
| 4 | LoRA and QLoRA: Efficient Fine-Tuning | 📖 + 🧪 | 3 hr |
Ship it. Scale it. Keep it working. Don't go broke.
| # | Module | Format | Est. Time |
|---|---|---|---|
| 5 | Safety, Guardrails & Content Filtering | 📖 + 💻 | 1.5 hr |
| Resource | Link |
|---|---|
| 📚 Glossary | 05-glossary.md |
Each phase ends with a capstone project you can actually put on your portfolio.
| Phase | Project | Skills Demonstrated |
|---|---|---|
| 0 | Foundations | LLM basics |
| 1 | Prompt Playground | Prompt engineering |
| 2 | CLI Chatbot | API calls, conversation history |
| 3 | Chat with Your Docs | RAG, vector DB, embeddings |
| 4 | Custom Fine-Tune | Dataset prep, LoRA, model training |
| 6 | Safety Implementation | Guardrails, content filtering |
Practical-AI-engineering/
├── 00-foundations_what_are_llms.md
├── 01-apis_quickstart.md
├── 02-prompt_engineering.md
├── 03-rag_pipeline.md
├── 04-finetuning_lora.md
├── 05-glossary.md
├── 06-safety_guardrails.md
├── README.md ← you are here
├── contributing.md
├── roadmap.md
└── LICENSE
| Icon | Meaning |
|---|---|
| 📖 | Written guide (Markdown) |
| 🧪 | Jupyter Notebook (runnable) |
| 💻 | Standalone code / project |
| 🏗️ | Capstone project |
| 🟢 | Beginner — no prior ML knowledge needed |
| 🟡 | Intermediate — comfortable with Python and APIs |
| 🔴 | Advanced — ML background helpful |
This curriculum is community-powered. All contributions welcome — big or small.
- Typo / small fix → open a PR directly
- Improve an explanation → open a PR with a brief note on what was unclear
- Add a new module → open an issue first so we can align on scope
- Translate to your language → see the Translations section
Please read contributing.md before submitting. Be kind.
| Language | Status | Maintainer |
|---|---|---|
| 🇬🇧 English | ✅ Complete | Core Team |
| 🇮🇳 Hindi | 🚧 In Progress | Contribute → |
| 🇪🇸 Spanish | 🚧 In Progress | Contribute → |
| 🇵🇹 Portuguese | 🙋 Needed | Contribute → |
| 🇨🇳 Chinese (Simplified) | 🙋 Needed | Contribute → |
| 🇯🇵 Japanese | 🙋 Needed | Contribute → |
- GitHub Discussions — questions, study groups, project showcases
- Issues — bug reports, content errors, suggestions
MIT — free to use, share, fork, and build on.
Attribution appreciated but not required.
Built with ❤️ by the community · Contribute · Star it ⭐
This curriculum is updated regularly. Watch the repo to stay notified.