How to Become a Great AI Engineer
Most people learn AI backwards. Here are 20 steps in the right order with a lesson for every single one.
Hi, I am Himanshu.
I worked as a Senior Software Engineer. Today I work as a Senior AI Engineer.
I learned AI engineering in 7 months. Since then I have built a lot of AI agents, and many of them now do real work for me every single day.
Right now I am working on something that would have sounded crazy to me a year ago. I am training my own model on a standalone server sitting in my home.
My first real AI project started with a simple question from my dad. ChatGPT gave him a confident but wrong answer about our electricity bill. So I built my first RAG system that could read our own documents and answer correctly. I wrote about it here.
Now I share what I learn with other engineers.
Almost every week I get a message on Instagram that looks like this.
“Bhaiya I have done a LangChain course. I made a chatbot. But I am getting rejected in every AI interview. What am I doing wrong?”
The person is usually not weak. Most of them are good developers. They work hard. They watch every new video.
So I ask them three small questions.
What does an embedding actually store?
Your chatbot has the right document. Why does it still give a wrong answer?
You changed your prompt. How do you know the new one is better?
Most of the time the reply is the same.
“I know how to use the tools. I don’t know what is happening inside.”
That line stayed with me. Because I made the same mistake when I started. I jumped to the shiny things first. I copied code that worked and felt good about it. Then the first time something broke I had no idea where to even look.
The problem was never hard work. The problem was the order.
When I sat down to build the AI Engineering track on AlgorithmXlr8 I spent most of my time on one question. What should a person learn first and what should come later?
This article is the answer. 20 steps in simple words. For every step I have added a lesson link so you can start today.
First, what does an AI engineer do?
An AI engineer does not invent new models. That is research work.
An AI engineer takes a model that already exists and builds a useful product with it. You connect it to data. You connect it to tools. You make sure it gives correct answers. You make it fast and cheap. Then you ship it.
Simple way to remember it. A researcher builds the engine. An AI engineer builds the car.
So you need two things. Good software skills and a clear idea of how models work. Here is the full path.
Phase 0: The basics
Step 1. DSA and system design
I know you want to start with AI. But most AI engineer interviews still have a coding round and a system design round. And every AI product is first a normal software product. It has APIs, a database and users who don’t like waiting.
If you already work as a developer just revise and move on. If you are in college please don’t skip this.
Read: DSA Patterns and High Level Design
Phase 1: Math and data
Step 2. Stats, probability and linear algebra
Don’t be scared of this. You only need the basics. What is a vector. What is a dot product. What does probability mean. That’s it. Embeddings and attention are built on these ideas.
Give it two or three weeks. Don’t sit on math for six months.
Lesson: Scalars, Vectors and Matrices
Step 3. NumPy and Pandas
Models work with numbers in arrays. Data comes in big tables. NumPy handles arrays. Pandas handles tables. You will use both every day.
Lesson: Introduction to NumPy
Step 4. Cleaning and plotting data
Real data is messy. Empty values. Repeated rows. Wrong formats. If you feed bad data to a model you get bad answers. Learn to clean data and draw simple charts so you can see what is going on.
Lesson: Introduction to Data Cleaning
Phase 2: Build and learn how models learn
Step 5. FastAPI
A model inside a notebook helps nobody. FastAPI lets you turn your code into an API that an app can call. Learn it early. After this every project you make can be used by real people.
Lesson: What is FastAPI?
Step 6. Machine learning basics
Regression. Decision trees. Clustering. Overfitting. These old ideas still matter. They teach you why models fail and how to test them. Many real problems are still solved with simple models.
Lesson: What is Machine Learning?
Step 7. Deep learning basics
Neural networks. How they learn. And then transformers, the idea behind every big AI model today. After this step words like tokens and context window will finally make sense.
Lesson: What is Deep Learning?
Step 8. PyTorch
Now write it yourself. Train one small model from start to end in PyTorch. Once you do this, AI stops feeling like magic.
Lesson: Introduction to PyTorch
Phase 3: Working with LLMs
This is where most people start. See how it is step 9 here. When you reach this point with strong basics you will learn it very fast.
Step 9. Prompting and model APIs
A good prompt is just clear instructions. Tell the model what to do. Give it the right information. Show an example. Ask for a fixed output format. Also learn how to call model APIs properly.
Get Himanshu Singour’s stories in your inbox
Join Medium for free to get updates from this writer.
Lesson: What is Prompt Engineering?
Step 10. RAG and vector search
If you go deep on only one topic, pick this one. It comes up in almost every AI interview I hear about.
RAG means two things. First find the right information. Then give it to the model so it can answer. That’s all.
One thing I learned the hard way. When a RAG chatbot gives a wrong answer, the model is usually not the problem. The search gave it the wrong pages. Always check the search part first.
Lesson: What is RAG?
Step 11. Fine-tuning
Fine-tuning means training an existing model a little more on your own data. Learn it. But don’t use it first. Most problems get fixed with a better prompt or better search. Fine-tune only when nothing else works.
Lesson: What is Fine-Tuning?
Step 12. MCP
MCP is a standard way to connect an AI model to tools and data. Think of it like a USB port for AI. One plug that works with many tools. It is becoming a must-know topic.
Lesson: What is MCP?
Step 13. Hugging Face
Hugging Face is where open models and datasets live. When you want to run your own model instead of using an API, you come here.
Lesson: Introduction to Hugging Face
Phase 4: Agents
Step 14. Agents and tool calling
An agent is an AI model that works in a loop. It thinks. It uses a tool. It checks the result. Then it decides if it is done or needs one more round.
Also learn when not to use an agent. Many times a simple script is enough.
Lesson: What is an Agent?
Step 15. LangChain and other frameworks
Now is the right time for LangChain. You already know what it does behind the scenes. So when something breaks you will know how to fix it.
Lesson: What is Orchestration?
Step 16. Build your own projects
Watching is not learning. Building is. Make your own small chatbot client. Your own vector database. Your own RAG system. These projects teach more than any certificate and they look great on a resume.
Project: Build Your Own RAG System
Step 17. LangGraph
For bigger agents that need many steps, retries or a human to approve something in the middle. LangGraph lets you draw your agent like a flowchart and run it.
Lesson: What is LangGraph?
Want to go deeper on agents? There is a full separate agent course too. Start here: What Is an AI Agent? Full course: AI Agent Development
Phase 5: Production
This is the part that makes you an engineer and not just a demo builder.
Step 18. Deployment
A demo works for one person. A real product works for thousands of people at the same time without a huge bill. Learn how to serve models, cache answers and track cost.
Lesson: Batch Inference
Step 19. Evaluation
How do you know your AI is giving good answers? You test it. Make a set of questions with correct answers and check your system against it every time you change something.
Lesson: Why Evaluation Matters
Step 20. Security
People will try to trick your AI. They will try to make it leak data or do things it should not. When your AI can send emails or touch a database, security is a must.
Lesson: Authentication
What not to learn first
Don’t start with LangChain. Understand the basics first.
Don’t try to train your own big model. No company expects that from you.
Don’t study only math for months. Learn a little and start building.
Don’t fine-tune before fixing your search. It costs more and usually fixes nothing.
Don’t chase every new model launch. Names change every week. Basics don’t.
Don’t collect certificates. Build projects.
How long will it take?
If you give around two hours a day, this is a normal pace. It is very close to how I did it myself in 7 months.
Some people will be faster. Some will be slower. Both are fine. Going in the right direction matters more than going fast.
Last thing
Remember that message? “I know how to use the tools. I don’t know what is happening inside.”
Tools will change every year. New frameworks will come. New models will come. But if you know what is happening inside, you can learn any new tool in a weekend. That is what makes someone really good at AI engineering.
The full roadmap with every step is here: algorithmxlr8.io/ai/engineering/home. Every step has a lesson so you can try it first. The full AI agent course is here: AI Agent Development.
If this helped you, save it and share it with one friend who is stuck watching tutorials. And tell me in the comments which step you are on. I read every comment.
Himanshu
