Artificial Intelligence and Machine Learning

About this course

Go from core fundamentals to advanced AI/ML skills through hands-on projects: Python, machine learning, Generative AI, prompt engineering, agentic AI and AI/ML operations.

Prerequisites: Starts from Python fundamentals. Ask an expert if you are unsure.

7

Learning units

50

Topics covered

7

Projects

20

Tools

1. 1

   Module 1

   Python

   • Fundamentals: setup, syntax, data types and operators
   • Flow control, lists, tuples, dictionaries, sets and comprehensions
   • Functions, file handling (CSV, XML, JSON, XLSX), lambda, map, filter and regular expressions
   • Logging, debugging, unittest, pytest, exception handling, Postman and Swagger
   • Modules, packages and project structure
   • Object-oriented programming
   • MySQL CRUD and FastAPI integration
   • Session management, async/await and JWT tokens
   • Scripting with os, subprocess, glob and sys
   • FastAPI, RESTful APIs, JSON schemas, Pydantic and bearer token authentication
   • Project: user management API
2. 2

   Module 2

   Machine Learning

   • Supervised, unsupervised and semi-supervised learning
   • ML vs AI vs LLM vs Data Science vs MLOps
   • Data cleaning, missing values, feature scaling and encoding, train/test split
   • Linear, polynomial and logistic regression, decision trees and random forest
   • Evaluation metrics: accuracy, precision, recall and F1-score
   • Training workflow, hyperparameter tuning, inference and model serialization
   • Projects: text classification and house price prediction
3. 3

   Module 3

   Agentic AI

   • Generative AI, prompt engineering and AI tools
   • Autonomous AI agents and their applications
   • LangChain, LangGraph, MCP and crewAI
   • Multi-step reasoning and orchestrator design
   • Tools, resources and memory registration with MCP
   • Integrating APIs and databases
   • Maintaining context and memory across conversations
   • Project: multi-reasoning AI assistant
4. 4

   Module 4

   Generative AI

   • Gen-AI architecture, and hosted vs open-source LLMs
   • LLM fundamentals and Transformers
   • GPT, BERT, Claude and LLaMA overview
   • Hugging Face Transformers, and LLM inference and optimization
   • Groq LLaMA models and AWS Bedrock Claude models
   • Prompt types: zero-shot, one-shot and few-shot
   • Chain-of-thought prompting and prompt optimization
   • RAG, embeddings, vector databases and ChromaDB
   • RAG workflow with LangChain
   • Project: RAG-based semantic search platform
5. 5

   Module 5

   AI/ML Operations

   • End-to-end AI/ML lifecycle and model governance basics
   • ML vs DevOps vs MLOps
   • Model packaging, serialization and versioning with Git and DVC
   • MLflow experiment tracking and model registry concepts
   • Kubeflow and SageMaker pipelines
   • Serving models with FastAPI and Streamlit
   • Real-time vs batch inference
   • Amazon SageMaker and Amazon Bedrock
   • Project: SageMaker-based MLOps pipeline
6. 6

   Module 6

   Projects

   • Capstone: full agentic AI system
   • Six further hands-on projects (listed below)
7. 7

   Module 7

   Career Guidance

   • Resume building, LinkedIn polishing and a personalized career roadmap
   • Weekly technical and HR mock interviews, with feedback
   • Weekly assignments, project reviews and development mentorship

Projects you will build

These are training projects. Please describe them honestly as training work on your resume and in interviews.

Tools and technologies

• Python
• NumPy
• Pandas
• FastAPI
• MySQL
• Scikit-learn
• PyTorch
• TensorFlow
• Hugging Face
• LangChain
• LangGraph
• MCP
• crewAI
• ChromaDB
• MLflow
• Kubeflow
• Amazon SageMaker
• Amazon Bedrock
• Docker
• Streamlit