← Back to the catalogueGenerative AI (Beginner to Advanced)
Beginner to Advanced
Level
Classroom . Online . Hybrid
Mode
Course overview
A single track that starts with no AI background and ends with a deployed generative AI application. The course explains what generative models are, how transformers produce text, and how the surrounding tools embeddings, vector stores, agents and fine-tuning fit together. Concepts are introduced where they are needed for the build in that module.
Learners work in Python on Google Colab with the OpenAI, Anthropic and Hugging Face APIs, and finish with a working assistant of their own choosing.
Who it is for
- Beginners with basic computer skills
- Developers new to AI work
- Students in engineering, science and MCA streams
- Professionals evaluating AI for their teams
Prerequisites
No AI background required. Basic Python is helpful and is revised in Module 2.
How it runs
Learn → Practise → Build → Experience → Demonstrate, ending in a capstone. Delivered by practitioners from the engineering bench, in Madurai, Coimbatore and online.
Final project
AI Assistant of the Learner’s Choice, Deployed and Documented
Programme sheet
The printed sheet carries the full module breakdown, labs, project work and certification path. Fees, dates and formats for the next intake are confirmed by the education team on enquiry.
Learning outcomes
01
Describe how generative models are trained and served.
02
Write Python that calls hosted and open models.
03
Design prompts that produce consistent structured output.
04
Build a retrieval pipeline over private documents.
05
Generate images, speech and audio alongside text.
06
Deploy an AI application with Streamlit or FastAPI.
07
Recognise cost, privacy and hallucination risks.
Module structure
10 modulesModule 01
Introduction to Generative AI
What is Generative AI . AI vs ML vs Deep Learning . Discriminative vs generative models . Where generative AI is used . Model families . Limitations and risks
Lab
Colab Setup . First API Call
Module 02
Python Essentials for AI
Data types . Functions . Files and JSON . Virtual environments . Working with APIs
Lab
Requests and JSON Parsing . Environment Variables
Module 03
How Language Models Work
Tokens . Embeddings . Attention . Transformer blocks . Temperature and sampling
Lab
Tokeniser Exploration . Embedding Similarity
Module 04
Prompt Engineering
Zero-shot . Few-shot . Role and system prompts . Structured output . Prompt chaining
Lab
Prompt Library . Output Validation
Module 05
Working with Models and APIs
OpenAI API . Anthropic API . Hugging Face Inference . Open models locally . Streaming responses . Rate limits and cost
Lab
Model Comparison Harness
Module 06
Retrieval-Augmented Generation
Document loading . Embedding models . Vector databases . Semantic search
Tools — LangChain, LlamaIndex, ChromaDB
Module 07
AI Agents and Tools
Agent loop . Tool calling . Function calling . Memory . Planning . Multi-agent basics
Tools — LangGraph, CrewAI
Module 08
Fine-Tuning and Customisation
When to fine-tune . Dataset preparation . Supervised fine-tuning . LoRA and QLoRA . Evaluation
Lab
LoRA Fine-Tune on Hugging Face
Module 09
Multimodal Generation
Image generation . Image editing . Speech to text . Text to speech . Video basics . Vision models
Tools — Stable Diffusion, Whisper, ElevenLabs
Module 10
Deployment and Final Project
Streamlit . Gradio . FastAPI . Environment secrets . Basic monitoring
Assessment & certification
Module assignments and labs
25%
Final project and review
40%
Learners who complete all modules, submit the final project and clear the review receive a course completion certificate from Kaizen Infinities Private Limited. Project work is documented for the learner's portfolio, and interview preparation is included in the closing sessions.
Career outcomes . Roles this programme prepares for
Generative AI DeveloperAI Application EngineerPrompt EngineerPython AI DeveloperAI Automation SpecialistTechnical AI Consultant
