Interactive Learning Path

AI Engineer Path.

Go from Python fundamentals to building production AI systems — covering ML foundations, LLMs, embeddings, RAG, agents, and real-world deployment.

This curriculum takes you from Python essentials through the full AI engineering stack — data handling, training intuition, working with foundation models, and shipping production-grade AI features that hold up under real traffic.

What you will learn

Python foundations required for data manipulation and model scripting.
Core ML concepts: supervised learning, validation that does not leak, and feature engineering.
Working with LLM APIs — prompt engineering, context design, and tool use.
Building retrieval-augmented generation pipelines with embeddings and vector stores.
Designing agents that plan, remember, and coordinate.
Evaluating, securing, deploying, and monitoring AI services in production.

Roadmap Curriculum

1

python Step 1 of 30

Python Variables and Type System

Understand variables, dynamic typing, scoping, and reference semantics in Python.

2

python Step 2 of 30

Python Data Types

Master Python's built-in data types: int, float, str, bool, None, and how to inspect and convert between them.

3

python Step 3 of 30

Python Functions and Parameters

Master defining functions, positional arguments, keyword arguments, and lambda functions.

4

python Step 4 of 30

Python Data Structures

Master lists, tuples, dictionaries, sets, and comprehensions with practical production-ready examples.

5

python Step 5 of 30

Error Handling in Python

Handle exceptions gracefully with try/except/finally, create custom exceptions, and use logging and traceback effectively.

6

python Step 6 of 30

Python Type Hints and Static Typing

Write self-documenting, safer Python code using type annotations, generics, Protocol, TypeVar, and runtime validation with Pydantic.

7

numpy Step 7 of 30

Creating NumPy Arrays

Master every array creation method — from Python sequences to ranges, zeros, ones, random values, and structured data.

8

pandas Step 8 of 30

Pandas DataFrames and Series

Master selection, filtering, column operations, and the core DataFrame API for daily data manipulation work.

9

ml Step 9 of 30

Introduction to Machine Learning

Understand the core concepts of machine learning — supervised vs unsupervised learning, the bias-variance tradeoff, and the ML workflow.

10

ml Step 10 of 30

Supervised Learning Algorithms

Understand and apply the core supervised learning algorithms — when to use each, how they work, and how to tune them.

11

ml Step 11 of 30

Machine Learning Cross-Validation

Understand and implement k-fold, stratified, time-series, and nested cross-validation for reliable model evaluation.

12

ml Step 12 of 30

Feature Engineering Pipelines

Build robust, production-ready feature engineering pipelines that prevent data leakage, handle edge cases, and plug into scikit-learn.

13

ml Step 13 of 30

Model Interpretability

Explain model predictions with SHAP values, LIME, partial dependence plots, and permutation importance.

14

llm Step 14 of 30

Introduction to LLM Engineering

Understand how large language models work, learn the OpenAI API, and write your first production LLM application.

15

llm Step 15 of 30

Prompt Engineering

Write effective prompts using few-shot examples, chain-of-thought reasoning, role prompting, and structured output techniques.

16

llm Step 16 of 30

LLM Context Engineering

Design effective context windows — managing conversation history, injecting knowledge, handling long documents, and optimizing token budgets.

17

llm Step 17 of 30

LLM Tool Use and Function Calling

Give LLMs the ability to call your functions, query databases, search the web, and take actions in the real world.

18

llm Step 18 of 30

LLM Embeddings and Vector Databases

Generate text embeddings, understand semantic similarity, and build search and recommendation systems with vector databases.

19

llm Step 19 of 30

RAG — Retrieval-Augmented Generation

Build a production RAG pipeline: chunk documents, embed them, store in a vector database, retrieve on query, and generate grounded answers.

20

ai-agents Step 20 of 30

Introduction to AI Agents

Understand what AI agents are, how the ReAct pattern works, and build your first autonomous agent that plans and executes multi-step tasks.

21

ai-agents Step 21 of 30

AI Agent Planning Patterns

Give agents the ability to decompose complex goals into steps, choose tools strategically, and recover from failures.

22

ai-agents Step 22 of 30

AI Agent Memory Systems

Give agents persistent memory — short-term conversation context, long-term key-value storage, and semantic memory with vector search.

23

ai-agents Step 23 of 30

RAG Agents

Build agents that combine retrieval-augmented generation with tool use — search, fetch, synthesize, and cite sources.

24

ai-agents Step 24 of 30

Multi-Agent Systems

Build systems where multiple AI agents collaborate — orchestrators, subagents, parallel execution, and human-in-the-loop patterns.

25

llm Step 25 of 30

LLM Evaluation

Measure LLM application quality systematically — reference-based metrics, LLM-as-judge, RAG evaluation, and regression testing.

26

llm Step 26 of 30

LLM Safety and Guardrails

Build safe LLM applications — input validation, output filtering, jailbreak detection, content moderation, and safe system prompt design.

27

llm Step 27 of 30

LLM Production Patterns

Build production-ready LLM applications — rate limiting, caching, cost optimization, error handling, and observability.

28

ai-agents Step 28 of 30

Agent Evaluation

Measure agent quality systematically — task completion rates, tool use efficiency, safety, and regression testing for agentic systems.

29

mlops Step 29 of 30

Model Serving and Deployment

Deploy trained ML models to production — REST APIs with FastAPI, BentoML, batch inference, and model versioning strategies.

30

mlops Step 30 of 30

MLOps Model Monitoring

Detect data drift, monitor model performance, set up alerts, and build retraining triggers for production ML systems.