Start Building These Projects to Become an LLM Engineer

First steps to become an LLM Engineer

Harshit Tyagi
5 min readSep 15, 2024

“Develop a habit of working on your own projects. Don’t let “work” mean something other people tell you to do. If you do manage to do great work one day, it will probably be on a project of your own. It may be within some bigger project, but you’ll be driving your part of it.” — Paul Graham

For aspiring AI professionals, becoming an LLM engineer offers an exciting and promising career path.

But where should you start? How should you learn?

In one of my previous posts I laid out the complete roadmap to become an AI / LLM Engineer. Reading this will give you insights on the type of skills you have to acquire and how.

The best way to learn — BUILD!

As Andrej Karpathy puts it:

Work on projects.

That is the best way to not just learn but really grok these concepts. It will further sharpen the skill to think about cutting edge use cases.

But the main challenge with this learning philosophy is that good projects are hard to find.

And that’s the problem I am trying to resolve. Helping people, including myself, discover and build practical and real-world projects that impart skills worth showcasing in your portfolio.

Your project can’t be just another analysis on Titanic dataset.

What should be your first project?

If you’re a beginner, your initial projects should showcase that you can comfortably build applications with LLMs i.e.

  • you know what APIs are,
  • you know how to consume them and,
  • how to build products that people actually want to use

Building a chatbot provides a great starting point but at this point everyone has developed one, there are many solutions for easy Streamlit based prototypes. So, you need to develop something that’s actually usable and has the potential to reach a wider audience.

What does that mean?

That means build a chatbot for WhatsApp or Discord or Telegram.

That means build a chatbot which solves a problem people struggle with, a problem companies have started to build solutions for.

If I had to pick a good and, arguably, the most common AI project that every company has started to work on is RAG-powered Chatbots.

But before you get to building RAG-powered bots, you should start building something slightly more basic with LLMs.

Here’s what I would do.

Project 1 — Summarise YouTube videos on WhatsApp

This chatbot allows users to send a YouTube video URL via WhatsApp, and it returns a summarized version of the video content.

  • Receives the YouTube URL.
  • Validates if the URL is correct.
  • Retrieves the transcript of the video
  • Uses LLM to analyze and summarize the video’s content.
  • Sends the summary back to the user.
https://www.wiplane.com/whatsapp-chatbot

Project #2 — Build a bot that can handle different types of user queries.

This bot acts as a customer service representative for an airline. It can answer questions related to flight status, baggage inquiries, ticket booking, and more. It uses Langchain’s Router and LLM models to dynamically generate responses based on the user’s input.

  • Different prompt templates are defined for various customer queries, such as flight status, baggage inquiries, and complaints.
  • Based on the query, the router selects the appropriate template and generates a response.
  • Twilio then sends the response back to the WhatsApp chat.
https://www.wiplane.com/whatsapp-chatbot

Project #3 — RAG-powered support bot — companies want this!

This chatbot answers questions related to airline services using a document-based system. The document is converted into embeddings, which are then queried using Langchain’s RAG system to generate responses.

  • The guidelines/rules document is embedded using FAISS and HuggingFace models.
  • When a user submits a question, the RAG system retrieves relevant information from the document.
  • The system then generates a response using a pre-trained LLM and sends it back via Twilio.
https://www.wiplane.com/whatsapp-chatbot

These 3 projects will set you off on a trajectory to keep iterating further.

That’s why I created this project-based course to help you start building with LLMs.

Project based course on building LLMs and RAG-powered WhatsApp bots

https://www.wiplane.com/whatsapp-chatbot

This course offers a great starting point which is the most crucial when acquiring a new skill.

It is a beginner track course where you start from learning to build with LLMs, then apply those skills to build 3 different types of LLM applications. Not just that you learn to serve your applications as WA chatbots.

Essentially, you end up making 3 projects in this course.

Customer Support is the most funded category in AI because it reduces the cost instantly if AI can handle communication with disgruntled users.

So, we build bots that can handle different types of queries, intelligent RAG powered bots which will have access to proprietary documents to provided up-to-date information to the users.

We’ll use free and open-source tools like LangChain, Hugging face, together ai’s free credits, and of course WhatsApp.

Check out the course preview:

For more details on the course, head over to:

Early bird pricing till September 25 — Get it for $9.99!

I want to make this affordably accessible for all those who are sincere about building with AI, hence I have priced it affordably at $14.99 USD.

BUT!

Because it is launch week, I am offering this for $9.99 USD for 10 days. 🤗

For more ideas

For more project ideas, head over to my repository here:

https://github.com/dswh/ai-engineer-roadmap/tree/main

--

--

Harshit Tyagi
Harshit Tyagi

Written by Harshit Tyagi

Director Data Science & ML at Scaler | LinkedIn's Bestselling Instructor | YouTuber

Responses (16)