Deep Learning Roadmap

Jun 16, 2025

A friend of mine is a Senior Deep Learning Engineer at Nvidia and the funny thing is he is almost close to retirement in just 6 years after his graduation at age 31. And over the weekend, I was in a conversation with him to pick his brains on how he mastered Deep Learning, landed the job at Nvidia , how he prepared for it. And he said , he did it in three phases.

Learning about Data Science and Machine Learning :

He was good at coding but he didn’t know anything about data science. And he didn’t want to spend time doing doing paid courses either as he was unsure if that’s what he wanted to do. So, he started off with free Youtube course

Stanford CS 229 : Intro to Machine Learning : Link

This will provide all the mathematical knowledge as well as the information on machine learning algorithms.

Stratascratch : Free Data Science Projects : Link

Advanced Machine Learning Knowledge :

For advanced Machine Learning , he started off with the course

Stanford CS231n: Deep Learning for Computer Vision

This is one of the best courses on Deep Learning. It is more focused on Deep Learning applications in Computer Vision, but it also covers ALL the basic and necessary aspects of Deep Learning too. So you should not worry about it being for Computer Vision at all. It also involved Neural Network Architecture mostly used in NLP.

NVIDIA SPECIFIC PREP :

He also used the below resources to further strengthen his prep. Three things to note :

Free : All links below are free of cost.
Lengthy learning curve : You will have to spend a lot of time building this tech stack. There is no easy way. One of the best ways to learn is if you are already at workplace and can do projects using this tech stack
CUDA and TensorRT : These are the main niche programming NVIDIA related skills worth getting experience in.