5 books x 7 courses x 19 notebooks x 21 video notes
| Course | Name | Duration | Difficulty | Salary |
|:------:|------|:--------:|:----------:|:------:|
| A | LLM Basics & Model Building | 8 weeks | L2 Intermediate | 30K-60K |
| B | Reasoning Models & Optimization | 4 weeks | L3 Advanced | 50K-100K |
| C | LLM Engineering & Production | 14 weeks | L3-L4 Advanced | 45K-120K |
| D | AI Governance & Compliance | 6 weeks | L2 Intermediate | 40K-52K |
| E | AI Product Management | 4 weeks | L1 Beginner | 35K-65K |
| F | LLM Engineering Decisions | 4 weeks | L4 Expert | 50K-130K |
| G | Financial LLM Ops & Compliance | 4 weeks | L3 Advanced | 45K-80K |
AI Engineer Track (26 weeks, 30K -> 120K):
Course-A (8w) -> Course-B (4w) -> Course-C (14w)
AI Governance Track (6 weeks, 40K -> 52K):
Course-D (6w)
AI Product Track (4 weeks, 35K -> 65K):
Course-E (4w)
AI Architecture Track (30 weeks, 30K -> 130K):
Course-A -> B -> C -> F
FinAI Track (24 weeks, 40K -> 80K):
Course-D (6w) -> Course-C (14w) -> Course-G (4w)
| Notebook | Topic | Course | Difficulty |
|----------|-------|--------|:----------:|
| 00 | Learning Roadmap | Pre-req | L1 |
| 01 | AI Assistant Basics | A pre-warmup | L1 |
| 02 | Model Building & API | A(W7), D(W2) | L2 |
| 03 | Data Governance & Security | D(W3) | L2 |
| 04 | LLM Book Ingestion | A(W1), D(W1) | L2 |
| 05 | Tokenization | A(W2) | L3 |
| 06 | Attention Mechanism | A(W3) | L3 |
| 07 | GPT Architecture | A(W4) | L3 |
| 08 | Pretraining | A(W5) | L3 |
| 09 | FineTuning | A(W6) | L3 |
| 10 | LoRA | A(W8) | L2 |
| 11 | Reasoning Model | B(W1-4) | L3 |
| 12 | StarTalent Architecture | C(W13-14), E, F | L4 |
| 13 | LLM Engineer Handbook | C(W1-14), D(W4-6) | L4 |
| 14 | RAG Building Blocks | C(W4, W9) | L3 |
| 15 | LangChain Runnable | C(W1, W7) | L3 |
| 16 | AI Engineering (Chip Huyen) | F(W1-4) | L4 |
| 17 | LLM Ops for Finance | G(W1-4) | L3 |
| 90 | Python Bootcamp | Pre-req (8 days) | L1 |
import sys, httpx
print(f"Python: {sys.version.split()[0]}")
print(f"Courses: A(8w) B(4w) C(14w) D(6w) E(4w) F(4w) G(4w)")
print(f"Notebooks: 19 | Books: 5 | Video Notes: 21")
try:
r = httpx.get("http://localhost:8080/v1/models", timeout=3)
print(f"Local LLM: ON - {r.json()['data'][0]['id']}")
except:
print("Local LLM: OFF - run `bash start.sh`")