Zero to AI

Zero to AI

A comprehensive curriculum from Python fundamentals to production-ready AI systems

Master machine learning, deep learning, LLMs, RAG, agents, and MLOps through hands-on notebooks and real projects.

31 Phases

950+ Notebooks

3 Learning Tracks

6-12 Months

Choose Your Track

Pick the path that matches your goals and timeline.

4-6 months

AI Engineer

LLMs, RAG, agents, deployment. Skip deep math. Build production AI applications fast.

Key phases: Embeddings, RAG, Prompt Engineering, Agents, MLOps

View track →

8-10 months

ML Engineer

Full foundation plus advanced topics. Deep understanding of models, math, and infrastructure.

Key phases: Math, Neural Networks, Fine-tuning, MLOps, Evaluation

View track →

6-8 months

Data Scientist

Statistics, experimentation, classical ML. Strong analytical foundation.

Key phases: Statistics, Causal Inference, Time Series, Evaluation

View track →

Curriculum

31 phases organized from fundamentals to cutting-edge research.

Foundations

Phase 0

Course Setup

Phase 1

Python

Phase 2

Data Science

Phase 3

Mathematics for ML

Core AI

Phase 4

Tokenization

Phase 5

Embeddings

Phase 6

Neural Networks

Applied AI

Phase 7

Vector Databases

Phase 8

RAG Systems

Phase 9

MLOps

Phase 10

Specializations

Advanced

Phase 11

Prompt Engineering

Phase 12

LLM Fine-tuning

Phase 13

Multimodal AI

Phase 14

Local LLMs

Phase 15

AI Agents

Supplementary

Phase 16

Model Evaluation

Phase 17

Debugging

Phase 18

Low-Code AI Tools

Phase 19

AI Safety

Phase 20

Real-Time Streaming

Research & Production

Phase 24

Advanced Deep Learning

Phase 25

Reinforcement Learning

Phase 26

Time Series

Phase 27

Causal Inference

Phase 28

Practical Data Science

Phase 29

AI Hardware

Phase 30

Inference Optimization

Quick Links

📖 Study Guide

Month-by-month learning plans for all three tracks.

Open guide →

💼 Interview Prep

15 core ML questions, coding problems, and system design walkthroughs.

Start prepping →

⚖️ Model Comparisons

Side-by-side comparisons of LLMs, embedding models, and tools.

Compare models →