Course Outline

Course Outline#

This is a 6-week live cohort based course. We will build 6 AI powered Apps, and learn the fundamentals of LLMs like tokenizations, embeddings, transformers, prompt engineering, RAG, fine tuning and AI Agents. The sessions will have a large hands-on component and we dig deep into mathematical concepts.

Session recordings will be made available.

Apart from the live sessions, every week we will have office hours to clear doubts and have general conversations about AI. These office hours are optional.


Program Outline#

Our first AI App

In our very first week, we will setup the tools needed to build AI powered apps.

Agenda

  • Build our first AI power app

  • Use Groq inference engine

  • Work with powerful LLama models

  • Learn about how LLMs represent words - tokenization

  • A peek into next week - embeddings and RAG

RAG-powered App

Having build our first app, we are now ready to solve practical business problems. Remember that LLMs don’t have access to your private data, and hence cannot answer questions relevant to your business problems. We address this issue by retrieval augmented generation (RAG)

Agenda

  • Learn how to connect the powerful LLMs to your private data

  • Ask questions to the LLMs specific to your business needs

  • Learn about vector embeddings and vector databases

  • Build your first RAG powered App

  • A peek into next week - prompt engineering

Prompt Engineering

Steering the run time behaviour of LLMs are extremely important for practical use cases. We’ll explore techniques to get the most out of these models through effective prompting.

Agenda

  • Learn about few-shot and zero-shot prompting techniques

  • Master chain-of-thought and tree-of-thought prompting

  • Implement system prompts and persona-based instructions

  • Build a specialized app using advanced prompting strategies

  • A peek into next week - transformers and attention mechanism

Transformer from scratch

Now that we know tokenizations, embeddings, and prompt engineering, we arrive at the central part of the LLM - the transformer architecture.

Agenda

  • Dissect the transformer architecture

  • Learn about the all-important attention mechanism

  • Implement GPT architecture from scratch

  • Understand how LLMs are learning probability distributions

  • We will also build an app to generate code

Fine-tuning LLMs

Powered by our knowledge of LLM architecture, we learn how to update the weights of an LLM based on finetuning on data that we are interested in.

Agenda

  • Understand when and why to fine-tune pre-trained models

  • Learn about parameter-efficient fine-tuning techniques (PEFT, LoRA)

  • Prepare datasets for fine-tuning and avoid common pitfalls

  • Implement a fine-tuning pipeline on a smaller open-source model

  • A peek into next week - building autonomous AI agents

Advanced AI Agents

The final week is where we use all our knowledge to build advanced AI Agents that can autonomously solve complex tasks.

Agenda

  • Understand the agent architecture and reasoning frameworks

  • Implement tools and function-calling capabilities

  • Build a multi-agent system with specialized roles

  • Create an autonomous agent that can plan and execute complex workflows

  • Learn other GenAI techniques - Gans, VAEs, Diffusion Models

Download PDF brochure

Prerequisite Knowledge#

While the course is accesible to a beginner audience, prior coding experience is expected.

You are expected have some understanding of coding - ideally in Python. If you are comfortable in other OOP languages such as Java and Javascript, you should feel comfortable following along. All apps we build will be in Python. If you have never coded in your life, this course is not for you.

You are expected to know how to add two vectors and visualize this geometrically, and have a basic understanding of conditional probability.

The course will be accessible to those without ML knowledge. However, a basic idea of loss functions and gradient descent will be helpful for students to fully grasp the more advanced concepts presented in later modules. While we’ll review these foundational elements at the beginning, familiarity with how models are trained by minimizing error and iteratively updating parameters will allow participants to engage more deeply with the practical exercises and implementation sections.

Refresher materials

Upcoming Cohort - June 2025#

📅 KEY DATES

  • Cohort Duration: June 7th - July 13th, 2025

  • Live Sessions: Saturdays & Sundays, 4:00 PM - 6:00 PM IST

  • Office Hours: Wednesdays, 9:30 PM - 10:30 PM IST


WHAT YOU’LL GET

  • ✓ Hands-on experience building cutting-edge GenAI applications
  • ✓ 6 weeks of structured learning with practical projects
  • ✓ Direct access to industry professionals
  • ✓ Exclusive WhatsApp community with peers and AI/ML experts

This is how our calendar will look like in the months of April and May.
The live sessions will be highly interactive. Clear all your doubts then and there.
Make sure that you optimally use our free flowing office hours.
Be part of a vibrat WhatApp group to constantly stay up to date with trends.

If you have any questions, feel free to reach out
Any Questions?

Contents