Course Overview
Become a job-ready AI Engineer and master the skills companies expect in 2026: Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI agents, and vector databases. You will follow an AI-engineer roadmap from foundations to deployment, so you can design, build, and ship production-grade AI features instead of just calling APIs.
This course is built for developers who want to transition into AI engineering roles and need a single, practical path that covers LLM concepts, RAG pipelines, agents, evaluation, and deployment. Every module ties skills directly to what AI engineer roadmaps and job descriptions list as must-have capabilities in 2026.
What you'll be able to do as an AI Engineer
Understand and explain the AI engineer skill stack: LLMs, RAG, AI agents, evaluation, and deployment.
Build LLM-powered applications with modern APIs and frameworks, using patterns you can discuss in interviews.
Design and implement RAG pipelines with embeddings, vector databases, and retrieval strategies that ground models in real data.
Create AI agents that use tools, plan multi-step workflows, and interact with external APIs like a real product feature.
Evaluate and debug AI systems using practical metrics - accuracy, hallucinations, latency, reliability - that matter in production.
Deploy AI services and integrate them into web backends or existing products so your work looks production-ready on a CV and portfolio.
Projects you'll add to your portfolio
An LLM-powered Q&A assistant grounded in your own documents using RAG and a vector database.
An AI agent that calls external tools and APIs to complete multi-step tasks, showcasing planning and tool-use.
A production-style AI microservice that exposes LLM and RAG functionality over an API, ready to plug into a real app.
Additional mini-projects that demonstrate prompt engineering, evaluation workflows, and AI-powered automation.
You can reference these projects in interviews, GitHub, and LinkedIn to prove you can design and ship full AI workflows, not just toy demos.
Who this course is for
Software Engineers and Backend or Full-Stack Developers targeting AI Engineer roles.
Data Scientists and ML Engineers who want to move into LLM and agent-centric work.
Career-switchers and motivated beginners who want a guided AI engineer roadmap instead of random tutorials.
Tech professionals who want to add AI Engineer skills to their current role and stand out in 2026.
Requirements
Comfortable with basic Python (loops, functions, packages); some API experience is helpful but not required.
No prior deep learning experience necessary; we cover the essentials as they relate to AI engineer work.
A computer with internet access to run notebooks, call APIs, and connect to vector databases.
If your goal is to apply for AI Engineer roles, talk confidently about RAG, agents, and vector databases, and ship projects that match modern roadmaps, this course is designed to get you there.
FAQ
FAQ area empty
Course curriculum
Chương 1 Introduction 4 bài · 17 phút
Chương 2 Development Environment Setup 6 bài · 13 phút
-
Development Environment Setup - Overview 0:50
-
Install Python on Windows - for WINDOWS USERS 2:54
-
Install Python on MAC - for MAC USERS 1:54
- Download Visual Studio Code Học thử 1:03
- Install the Python Extension Pack for VS Code Học thử 1:56
-
Running First Python Program in VS Code 4:11
Chương 3 Download Source code for the AI, LLM Engineering Mastery 1 bài
Chương 4 Do You Know Python? 1 bài · 1 phút
-
Python Deep Dive - Introduction and Overview 0:53
Chương 5 OPTIONAL - Python Deep Dive - Master Python Fundamentals 77 bài · 6 giờ 25 phút
-
What is Python and Where It's Used? 3:02
-
Python Compilation & Interpretation Process 2:43
-
Download Python Fundamentals Code
-
Declaring Variables in Python 4:32
-
Data Types 5:29
-
Python f-Strings 3:26
-
Numbers - Integers and Floats 3:25
-
Introduction to Lists - Accessing and Modifying Them 7:37
-
F-Strings & Individual Values from a List 3:07
-
Sorting a List and Getting a List Length 6:30
-
Lists and Loops - Looping through a List 4:12
-
Making a List of Numbers with Loops and the Range Function 5:59
-
Statistics Functions for Numbers 2:28
-
Generate Even Numbers with the List and Range 2:49
-
Important: Code Organization Note 0:36
-
List Comprehension 3:51
-
Tuples 3:03
-
Branching - If Statements and Booleans 6:47
-
The Elif and the in Keywords 3:55
-
Hands-on - Using AND and OR Logical Operators 5:51
-
AND OR Logical Operators 1:05
-
Checking for Inequalities 1:52
-
Hands-on - Inner If-Statements 3:35
-
Data Structures - Dictionaries - Introduction and Declaring and Accessing Values 5:49
-
Modifying a Dictionary 4:39
-
Iterating Through a Dictionary 4:05
-
Nested Dictionaries and Looping Through Them 6:53
-
Looping through a Dictionary with a List Inside 3:40
-
User Input and While Loops - User Input - Introduction 6:34
-
Hands-on - Odd or Even Number 4:53
-
While Loops & Simple Quit Program 7:25
-
Hands-on - Quiz Game 7:49
-
Removing all Instances of Specific Values from a List 1:24
-
Hands-on Dream Travel Itinerary Program - Filling a Dictionary with User Input 8:41
-
Functions - Introduction 4:19
-
Passing Information to a Function (parameters) 4:24
-
Positional and Named Arguments 1:49
-
Default Values - Parameters 3:05
-
Return Values from a Function 4:09
-
Hands-on - Returning an Integer & Intro to DocString 4:55
-
Functions - Passing a List as Argument 2:29
-
Passing an Arbitrary Number of Arguments to a Function 5:37
-
Introduction to Modules - Importing Specific functions from a Module 6:49
-
Using the "as" as an Alias 1:40
-
Classes and OOP - Object Oriented Programming - The "init and "str" methods 9:55
-
Adding More Methods to the Class 2:13
-
Setting a Default Value for an Attribute 1:46
-
Modifying Class Attribute - directly and with Methods 2:43
-
Inheritance - Create an Ebook - Child Class 11:10
-
Overriding Methods 5:45
-
Creating and Importing from a Module 5:22
-
The Object Class - Overview 8:13
-
The Python Standard Library 1:31
-
Random Module - Random Fruit Hands-on 6:34
-
Hands-on - Random Fruit with Choice Module Method 4:08
-
Using Datetime Module 6:25
-
Writing & Reading Files - Do Useful Tasks with Python - Do amazing things 0:41
-
The Path Class & Reading a Text File 4:51
-
Resolving Path - Reading From a Subdirectory with Path 2:21
-
Path Properties Overview 3:20
-
Writing to Text file with Path 2:43
-
Read and Write to File Using the "with" Keyword 4:24
-
Handling Exceptions 5:30
-
The "FileNotFound" and "IndexError" Exceptions Types 3:56
-
Custom Exception Creation and handling 8:20
-
JSON - Reading and Writing to a JSON File 7:27
-
Hands-on - Writing and Reading - Countries to JSON file 8:35
-
Hands-on - File Organizer 13:18
-
Python Virtual Environment and PIP 3:52
-
Setting up Virtual Environment and Installing a Package 6:54
-
Hands-on Watermarker Python Tool 1:00
-
Building an Image Watermarker in Python - Part 1 17:17
-
Generating the Watermarked Images 10:47
-
Reading CSV File - Introduction 5:57
-
Getting the CSV header Position 4:41
-
Reading Data from a CSV Column 3:45
-
Plotting a Graph with CSV Data 12:05
Chương 6 Deep and Machine Learning Deep Dive 11 bài · 1 giờ 1 phút
-
Deep and Machine Learning Deep Dive - Overview and Breakdown 9:26
-
Deep Learning Key Aspects 10:49
-
Deep Neural Network Dissection - Full Dive with Analogies 9:22
-
The Single Neuron Computation - Deep Dive 5:38
-
Weights - Deep Dive 2:58
-
Activation Functions - Deep Dive with Analogies 6:14
-
Deep Learning Summary 1:59
-
Machine Learning Introduction - Machine Learning vs. Deep Learning 4:52
-
Learning Types - Education System Analogy 5:43
-
Comparative Capabilities Deep Learning and Machine Learning and AI - Summary 4:28
-
Deep Learning & Machine Learning Knowledge Check
Chương 7 Generative AI (GenAI) - Deep Dive 4 bài · 12 phút
-
GenAI Introduction and Architecture Overview 4:37
-
GenAI Key Technologies - Limitations and challenges 5:30
-
GenAI Key Components Overview and Summary 1:55
-
Generative AI Fundamentals Knowledge Check
Chương 8 LLMs (Large Language Models) - Fundamentals - A Deep Dive 8 bài · 49 phút
-
LLMs - Overview 7:07
-
The Transformer Architecture - Fundamentals 7:33
-
The Self-Attention Mechanism - Analogy 5:25
-
The Transformers Library - Deep Dive 4:26
-
HANDS-ON - Create a Simple LLM from the Transformers Library - Simple 9:39
-
HANDS-ON - Hands-on Enhanced Transformers LLM 10:22
-
Open-source vs. Closed-source Models - Overview 4:53
-
LLMs & Transformer Architecture Knowledge Check
Chương 9 LLM APIs: Models, Tokens, Reasoning & Cost 9 bài · 1 giờ 11 phút
-
Get Your API Keys: Anthropic, OpenAI, Google 3:25
-
HANDS-ON - Setup: uv, Keys, and Your First Call to Three Providers 12:57
-
HANDS-ON - Tokens, Next-Token Prediction & the Two Limits 8:43
-
HANDS-ON - Reasoning Models, Effort, and the End of Temperature 8:03
-
HANDS-ON - Reading the Model Landscape (Without Memorizing It) 11:30
-
HANDS-ON - Cost Math & Prompt Caching 13:11
-
API vs Local vs Fine-Tuned: A Decision Framework 10:45
-
Exercise: Write a Model Selection Memo 2:31
-
Write a Model Selection Memo
Chương 10 Prompt Engineering - Communicating with LLMs - Deep Dive 13 bài · 54 phút
-
Prompt Engineering Introduction 4:01
-
Prompt Engineering and Types - Why it Matters 8:26
-
HANDS-ON - Simple Prompting Example 5:19
-
Advanced Prompting Techniques and Challenges 7:59
-
HANDS-ON - Few-shots Prompting 4:55
-
HANDS-ON - Zero-shot Prompting 2:26
-
HANDS-ON -Chain-of-Thoughts Prompting 2:54
-
HANDS-ON - Instructional Prompting 2:58
-
HANDS-ON - Role-Playing and Open-ended Prompting 3:13
-
Temperature, Top-p, and What Replaced Them 4:25
-
HANDS-ON - Prompt Techniques Combination and Streaming 4:43
-
Prompt Engineering Summary and Takeaways 2:17
-
Prompt Engineering Mastery Quiz
Chương 11 Ollama & Open-Source Models - Complete Guide 25 bài · 1 giờ 44 phút
-
Ollama - Introduction 2:01
-
Download Source Code and Resources
-
Ollama Deep Dive - Ollama Overview - What is Ollama and Advantages 6:24
-
Ollama Key Features and Use Cases 3:58
-
System Requirements & Ollama Setup - Overview 0:55
-
HANDS-ON - Download and Setup Ollama and Llama3.2 Model 8:10
-
Ollama Models Page - Overview 7:27
-
Ollama Model Parameters Deep Dive 6:22
-
Understanding Parameters and Disk Size and Computational Resources Needed 2:52
-
Ollama CLI Commands -Pull and Testing a Model 4:01
-
Pull in the Llava Multimodal Model and Caption an Image 5:14
-
Summarization and Sentiment Analysis & Customizing Our Model 7:48
-
Ollama REST API - Generate and Chat Endpoints 4:40
-
Ollama REST API - Request JSON Mode 2:50
-
Ollama Models Support Different Tasks - Summary 1:07
-
Different Ways to Interact with Ollama Models 2:02
-
Ollama Model Running Under Msty App 11:02
-
Ollama Python SDK for Building LLM Local Applications 2:29
-
HANDS-ON - Interact with Llama3 in Python Using Ollama REST API 5:15
-
Ollama Python Library - Chatting with a Model 6:12
-
Chat Example with Streaming 1:33
-
Using Ollama Show Function 1:59
-
Create a Custom Model in Code 3:49
-
Local vs API: Same Prompt, Two Models 5:26
-
Ollama & Open-Source Models Knowledge Check
Chương 12 Context & Memory Management for LLMs - Deep Dive 5 bài · 40 phút
-
HANDS-ON - Context and Memory Management Overview 9:25
-
What is Context and Memory Management - Deep Dive 9:52
-
HANDS-ON - Adding Memory and Context to Chatbox 19:23
-
Summary 1:03
-
Context & Memory Management Knowledge Check
Chương 13 Logging in LLM Applications - Deep Dive 5 bài · 28 phút
-
Logging - Introduction - What and the Why 4:41
-
Logging in LLM Applications and Logging Life Cycle 5:24
-
HANDS-ON - Chatbot with Logging 16:53
-
Summary 0:53
-
Logging in LLM Applications Knowledge Check
Chương 14 RAG - Retrieval-Augmented Generation - Deep Dive 8 bài · 23 phút
-
RAG Introduction - What is it? 3:01
-
RAG Key Components - The RAG Triad 3:47
-
RAG vs. Pure GenAI Models 2:00
-
RAG Deep Dive - Full Diagram Walkthrough 5:40
-
RAG Benefits and Practical Applications 5:00
-
RAG Challenges 1:17
-
RAG Fundamentals - Takeaways - Summary 2:08
-
RAG Fundamentals Knowledge Check
Chương 15 Vector Databases and Embeddings - Deep Dive 34 bài · 2 giờ 50 phút
-
Vector Databases and Embeddings for RAG Workflows - Introduction 0:47
-
Download Source code
-
Introduction to Vector Databases - Full Overview 4:43
-
Why Vector Databases 11:33
-
Vector Databases - Benefits and Advantages 3:28
-
Traditional vs. Vector Databases - Limitations and challenges 6:31
-
Vector Databases & Embeddings - Full Overview 8:55
-
Embeddings vs. Vectors - Differences 3:25
-
Vector Databases - How They Work and Advantages 3:37
-
Vector Databases Use Cases 5:51
-
Vector and Traditional Databases - Summary 0:33
-
The Top 5 Vector Databases - Overview 8:13
-
Building Vector Databases - Dev Environment Setup 1:02
-
Setup VS-Code, Python and OpenAI API Key 4:38
-
Chroma Database workflow 7:15
-
Creating a ChromaDB and Adding Documents and Querying 9:39
-
Looping Through the Results & Showing Similarity Search Results 5:37
-
Chroma Default Embedding Function 6:25
-
Chroma Vector Database - Persisting Data and Saving 10:09
-
Creating an OpenAI Embeddings - Raw without Chroma 7:16
-
Using OpenAIs Embedding API to Create Embedding in ChromaDB 8:25
-
Vector Databases Metrics and Data Structures 4:18
-
Summary 0:46
-
Vector Similarity Deep Dive - Cosine Similarity 8:08
-
Euclidean Distance - L2 Norm 1:29
-
Dot Product 2:04
-
Summary 1:09
-
Vector Databases and LLM - Deep Dive 3:48
-
Loading all Documents 7:41
-
Generating Embeddings from Documents and Insert to Vector Database 8:18
-
Getting the Relevant Chunks when Given a Query 5:48
-
Using OpenAI LLM to Generate Response - Full Workflow 6:50
-
Summary 1:31
-
Vector Database Mastery Quiz
Chương 16 HANDS-ON - RAG PDF Workflow - Build RAG Workflows Deep Dive 6 bài · 44 phút
-
Building a RAG Pipeline - Overview 1:32
-
First RAG Workflow Architectural Diagram 4:41
-
Setting up the Embedding Model Class 9:31
-
HANDS-ON - Building and Showcasing the RAG Workflow 15:35
-
HANDS-ON - RAG Workflow with UI - Streamlit 9:20
-
First RAG Pipeline Summary 3:22
Chương 17 HANDS-ON - Build a PDF RAG System with Text Chunking 5 bài · 41 phút
-
PDF RAG Workflow - Architecture Overview 4:43
-
PDF and Chunk Processing and Chunk Overlap - Deep Dive 11:39
-
Setting up the SimpleRAGSystem Class and Methods 10:18
-
Testing the PDF RAG System 12:41
-
Simple PDF RAG Workflow - Summary 1:56
Chương 18 LLM Tools and Frameworks - LangChain Deep Dive 14 bài · 1 giờ 36 phút
-
LLM Frameworks Introduction - LangChain Fundamentals 3:38
-
What is LangChain and and Main Components 5:52
-
LangChain Setup and ChatModel 9:39
-
Hands-on - LangChain ChatPromptTemplates 6:41
-
Indexes, Retrievers and Data Preparation - Overview 4:03
-
Hands-On - LangChain TextLoaders 4:39
-
Hands-on: Text Splitting and Cleaning 7:48
-
Hands-on: Embeddings and Retriever with FAISS VectorStore 10:50
-
LangChain TextSplitter - Deep Dive 3:20
-
LangChain DirectoryLoader 5:15
-
LangChain PDFLoader 2:47
-
Hands-on: LangChain Chains 5:34
-
Hands-on - Simple RAG System with Chat and LangChain Chains 6:39
-
Hands-on: Full RAG System QA Bot Using LangChain 19:13
Chương 19 HANDS-ON - Building LLM Applications with LangChain 9 bài · 1 giờ 28 phút
-
LLM Application - News Summarizer - Architectural Overview 3:11
-
News Summarizer - Full Implementation 19:19
-
LLM Application - Youtube Video Summarizer - Architectural Overview 2:39
-
Youtube Video Summarizer & Q&A Dependency Setup 4:08
-
Youtube Video Summarizer Class Setup and Walkthrough 14:38
-
Youtube Video Summarizer Q&A - Testing the Workflow 10:00
-
LLM Application - Voice Assistant RAG System - Architectural Overview 3:45
-
Voice Assistant RAG System - Demo 5:02
-
Voice Assistant RAG System - Walkthrough and Demo 25:22
Chương 20 Advanced RAG Techniques - Naive vs Advanced RAG Techniques 14 bài · 1 giờ 34 phút
-
RAG and the RAG Triad - Quick Overview and Recap 3:03
-
What is RAG and Naive RAG Overview and Pitfalls - Motivation 8:50
-
Deep Dive into Each Naive RAG Drawbacks 6:11
-
Advanced RAG Technique - Query Expansion with Multiple Queries - Overview 3:05
-
Hands-on - Query Expansion with Multiple Queries - Generate Multiple Queries 6:46
-
Query Expansion Workflow Architectural Diagram 2:14
-
Hands-on- Setting up the Workflow and Code Walkthrough 18:25
-
Query Expansion Full RAG Workflow 7:53
-
Query Expansion with Multiple Queries Downsides & Summary 1:23
-
Re-Ranking & Cross-encoder and Bi-encoders - Overview 4:50
-
Reranking Technique RAG System Workflow Architecture 3:05
-
Cohere Rerank API Key Setup 4:45
-
Hands-on - Re-ranking Implementation with Cohere - Full Implementation 22:42
-
Re-ranking Summary 0:57
Chương 21 Multimodal RAG - Deep Dive 16 bài · 1 giờ 17 phút
-
Multimodal RAG Source Code
-
RAG & Multimodal RAG - Recap and Overview 4:17
-
RAG Benefits and Practical Applications 4:14
-
Multimodal RAG - Overview & Motivation and Benefits - How it Works 8:54
-
How Search Is Integrated into a Multimodal RAG System - Full Workflow 3:19
-
Why Multimodal Search is so Powerful 2:53
-
Visual Explanation Why Multimodal Search is so Powerful 4:47
-
HANDS-on: Multimodal Search System setup - Create Embeddings from Images 7:57
-
Finish the Multimodal Search System 9:17
-
HANDS-ON - Multimodal Recommender System - Overview 3:28
-
Getting our Dataset from HuggingFace & showing Number of Rows 3:27
-
Saving Images Embeddings to Vector Database 3:00
-
Testing our MultiModal Recommender System - Fetching the Correct Images 3:52
-
Setting up the RAG Workflow 8:12
-
Putting it all Together and Testing the Multimodal Recommender RAG System 6:29
-
Adding a Streamlit UI to the Multimodal Recommender System 2:58
Chương 22 AI Agents & Agentic Workflows - Deep Dive 30 bài · 2 giờ 45 phút
-
AI Agents Deep Dive - A Full Overview 7:16
-
Agents Characteristics and Use Cases 2:51
-
Download Source Code for AI Agents Section
-
Building our First AI Agent - Project Setup (OpenAI API) 3:35
-
Build our First AI Agent - Creating the Agent Class and Prompt 10:33
-
First AI Agent - Running our First Agent and Seeing the Results 7:36
-
Passing Complex Queries Through the Agent 11:51
-
First Agent - Using a Loop to Automate our Agent 10:02
-
Adding Interactive to Our Agent - Console App 4:34
-
Agent Introduction - Section Summary 3:30
-
AI Agents Knowledge Check
-
LangGraph - Overview & Key Concepts 5:25
-
LangGraph - How It Helps Build AI Agents 2:52
-
LangGraph Core Concepts - Simple Flow Diagram 2:17
-
LangGraph - Data and State - Overview 2:02
-
Building a Simple Agent with LangChain 11:13
-
LangGraph Simple Bot - Streaming Values - Console App 5:00
-
Adding Tools to our Basic LangGraph Agent 6:57
-
Adding tools to the Agent - Part 1 6:07
-
Adding Tools to the Agent - Using Built-in Tools - Part 2 4:35
-
Adding Memory to Our Agent State 8:01
-
Adding Human-in-the-loop to the AI Agent 5:12
-
Building AI Agents with LangChain - Section Summary 1:23
-
Hands-on - Build a Financial Report Writer AI Agent 1:20
-
Agent State and Prompts Setup 6:14
-
Creating All Nodes - Functions 10:20
-
Adding Nodes and Edges and Running our Agent 11:29
-
Adding a GUI to the Agent with Streamlit 7:45
-
Optimization Techniques - Overview 3:21
-
Financial Report Writer AI Agent - Course Summary 1:32
Chương 23 Fine-tuning LLMs 8 bài · 47 phút
-
Read First: OpenAI Fine-Tuning Has Changed
-
Fine-tuning Introduction - Overview 3:25
-
Fine-tuning Techniques - Overview 8:12
-
Fine-tuning Comparison of Techniques 2:09
-
Fine-tuning General Process - Overview 2:25
-
Fine-tuning OpenAI Models Pricing 4:07
-
HANDS-ON - Fine-tuning an OpenAI Model - Full Walkthrough 22:09
-
Creating a Chatbot with our Fine-tuned Model and Testing 4:07
Chương 24 Fine-Tuning Technique - LoRA Deep Dive 9 bài · 1 giờ 5 phút
-
LoRA Introduction - Benefits 4:27
-
LoRA Deep Analysis 4:39
-
LoRA Implementation Strategy Workflow 3:23
-
Hands-on - Training Models - LoRA and PEFT 14:27
-
Running LoRA Model Fine-tuning and Testing 8:07
-
Creating an API Service to Interface with Our Fine-tuned Models 9:51
-
Testing our LoRA Model API Endpoint 6:41
-
Chatting with LoRA Fine-tuned Models 5:31
-
Full LoRA Workflow - Train and Chat with Fine-tuned Models 8:01
Chương 25 Wrap up and Next Steps 1 bài · 4 phút
-
Wrap up and Next Steps 3:50
Requirment
-
Basics of Programming - Python Fundamentals INCLUDED
Outcomes
-
Master the architecture and workflow of a RAG system for processing PDFs and multimodal data.
-
Master the Fundamentals of AI, Machine Learning and Deep Learning (Basics)
-
Master LangChain tools, frameworks, and workflows, including embedding techniques and retrievers.
-
Fine-tuning models with OpenAI, LoRA, and other techniques to customize AI responses.
-
Develop AI-driven applications with advanced RAG techniques, multimodal search, and AI agents for real-world use cases.
Instructor
Paulo Dichone | Software Engineer, AWS Cloud Practitioner & Instructor
0.0
-
0 Student
-
1 Course
-
0 review
View Details