Gen AI and Agentic AI Engineering

Categories: AI Learning
Wishlist Share
Share Course
Page Link
Share On Social Media

About Course

AI Engineer Course Outline
Module 1: Python Foundations for AI
– Python essentials for AI workflows
– NumPy & Pandas for data operations
– Reading/Wrangling real datasets
– Hands‑on mini‑project: Data cleaning pipeline
Module 2: Machine Learning Core Concepts
– Supervised vs Unsupervised learning
– Train/validation/test splits
– Linear & Logistic Regression
– Decision Trees & Random Forests
– Evaluation metrics (Accuracy, F1, ROC‑AUC)
– Hands‑on: Build & evaluate ML models
Module 3: Vector Embeddings & Modern NLP Foundations
– What embeddings are & why they matter
– Tokenization & text preprocessing
– Transformer intuition
Module 4: Practical Transformers for Industry
– HuggingFace pipelines
– Loading pre‑trained models
– Fine‑tuning for classification
– Hands‑on: Fine‑tune a text classifier
Module 5: RAG Systems & Document Intelligence
– What is RAG & why enterprises use it
– Chunking strategies
– Vector DBs (FAISS / Chroma)
– Building a working RAG pipeline
– Evaluating RAG systems with RAGAs
Module 6: AI Deployment & Real‑World Integration
– Building APIs for AI models
– Streaming responses
– Using AWS Bedrock / Azure / Local models
– Final capstone project: End‑to‑end AI solution

Show More

What Will You Learn?

  • 1. Python Foundations for AI
  • Python essentials used in real AI workflows
  • Working with NumPy & Pandas for data manipulation
  • Reading, cleaning, and preparing real-world datasets
  • Build a hands-on data-cleaning mini-project
  • 2. Core Machine Learning Concepts
  • Supervised vs unsupervised learning fundamentals
  • Creating proper train/validation/test splits
  • Implementing Linear & Logistic Regression
  • Understanding Decision Trees & Random Forests
  • Evaluating models using Accuracy, F1-Score, ROC-AUC
  • Build & evaluate complete ML models
  • 3. Vector Embeddings & Modern NLP
  • What vector embeddings are and why they matter
  • Text preprocessing & tokenization techniques
  • Intuition behind Transformers
  • 4. Practical Transformers for Industry
  • Using HuggingFace pipelines for real-world tasks
  • Loading & applying pre-trained transformer models
  • Fine-tuning models for text classification
  • Hands-on transformer fine-tuning project
  • 5. RAG Systems & Document Intelligence
  • Understanding Retrieval-Augmented Generation (RAG)
  • Smart chunking strategies for documents
  • Using Vector Databases like FAISS & Chroma
  • Building a fully functional RAG pipeline
  • Evaluating RAG systems with RAGAs
  • 6. AI Deployment & Real-World Integration
  • Building & deploying APIs for AI models
  • Generating and streaming responses efficiently
  • Using AWS Bedrock, Azure, or local LLMs
  • Final capstone: Build an end-to-end AI solution

Course Content

AI Engineering Class 1

  • Class No 1
    00:00

AI Engineering Class 2

AI Engineering Class 3

AI Engineering Class 4

AI Engineering Class 5

Student Ratings & Reviews

No Review Yet
No Review Yet