Course Introduction. Framing the concepts

1. Course Introduction
2. Framing the concepts: Machine Learning, AI, Generative AI, Large Language Models
3. At a glance: how LLMs and ChatGPT work
4. Real examples and business applications

Get familiar with Python

1. Set up the environment: Python, VS Code
2. Programming basics: variables, basic data types and operations
3. Conditional statements (if/elif/else) and loops (for/while)
4. Data structures: lists, tuples, dictionaries
5. Functions
6. Virtual environments
7. Working with Git and Github

Working with Git and GitHub

Data Science and Machine Learning Tools Overview

Hands-On with Pandas in Jupyter Notebook

Practice: Python for data analysis

Machine Learning basics

1. What ML models are and how they learn
2. Supervised, Unsupervised, and Reinforcement Learning
3. Data preparation and feature engineering (scaling, one-hot encoding)
4. Introduction to scikit-learn
5. Simple regression example
6. Simple classification example
7. Model evaluation: accuracy, confusion matrix, precision, recall

Project 1: Build a Spam Classifier

1. Project 1: Build a Spam Classifier

NLP Basics

1. Introduction to Natural Language Processing (NLP)
2. Text preprocessing: cleaning and normalizing text
3. Tokenization
4. Text vectorization: Bag-of-Words (BoW), TF-IDF, word embeddings
5. Basic language tasks
6. Practical example: Simple Sentiment Analysis model (data prep → vectorization → training → evaluation)

Introduction to LLM and ChatGPT

1. How neural networks work
2. How LLMs learn: understanding the Transformer architecture
3. How LLMs are used in real-world projects
4. Introduction to the OpenAI API: settings, API keys, pricing
5. Basic API requests with Python

Prompt Engineering

1. System prompt, context, constraints
2. Few-shot learning, Chain-of-Thought (CoT), structured JSON output
3. Handling hallucinations
4. Practice: create an LLM assistant with a predefined personality
5. Advanced API settings: temperature, max_tokens

Vibe Coding with AI assistants

1. What VibeCoding is. Overview of the ecosystem: Replit, Bolt, GitHub Copilot, Cursor, Claude Code, Google Antigravity
2. Techniques for effective collaboration with AI when generating and refactoring code
3. Validating generated code and identifying errors

Project 2: Build AI Assistant

1. Building a Chatbot with Gemini API, Transformers, Ollama
2. Designing the logic: connecting the ML model with ChatGPT/Gemini API for contextual responses
3. Implementing the logic
4. Testing and fine-tuning the chatbot based on user sentiment

Build User Interface (UI) with Streamlit

1. Introduction to Streamlit for a web interface
2. Implementing the UI and connecting it to the AI logic

Cloud Deployment

1. Preparing for deployment: requirements.txt, dependency management
2. Practical Session: deploying the AI assistant online (Streamlit Cloud or similar)
3. Testing and sharing the project

Final Project: From Idea to Production

1. Selecting and planning your AI Assistant
2. Building the end-to-end ML lifecycle
3. Modern AI tools for rapid prototyping (Vibe Coding)
4. Documentation, README, and project architecture

Discuss your portfolio and CV tips

1. Building a compelling AI/ML Portfolio (GitHub, Personal Website)
2. CV best practices for AI Engineers in 2025/2026
3. LinkedIn optimization and networking
4. Interview preparation for AI roles

Advanced topics: RAG with LangChain

1. Introduction to RAG
2. Building a RAG system with LangChain
3. Testing and fine-tuning the RAG system

Useful VS Code Shortcuts

Online Resources