GitHub radar
Prep for ML engineer interviews by building algorithms from scratch
This is a GitHub repo of Python notebooks for Machine Learning Engineer interview prep — walk through the code with your AI agent and see how the algorithms actually work.
A set of Python notebooks with core machine learning algorithms implemented from scratch, no AI frameworks, plus separate sets of interview-style practice problems.
When it helps
Useful if you're prepping for an MLE technical interview and want to understand algorithms at the code level, not just memorize answers. Not for you if you want a guided course — this is just code and minimal text.
Pros
- Walk through each algorithm's math line by line, not just in theory
- Includes real interview questions from companies like Shopify, LinkedIn, Meta
- No GPU needed — runs on a regular laptop
- Lets you test how well you understand core algorithms
Cons
- Just code and text — no interface, most of the work is on you
- You need to read and write code yourself, not just watch
How to set it up — step by step
- 1Open your AI agent (Claude Code, Codex) in your project folder.
- 2Send the agent the text from the block below.
- 3Check that the Python environment with numpy and PyTorch installs without errors.
- 4Ask the agent to explain each implementation as it goes, starting with multi-head attention.
- 5Go through the other notebooks — ML/CS problems and interview-style questions.
Text for your agent
Copy this and send it to your agent — Claude Code, Codex, any of them:
Open the MLE_Coding_Interview_Guide.ipynb notebook from https://github.com/jyotipmahes/ML-Interview-Prep, set up a Python environment with numpy and PyTorch so I can run the code, and explain each implementation in plain language as we go, starting with multi-head attention.
Runs on a regular laptop — you need Python with numpy and PyTorch, no GPU required.
Open on GitHub▌ More finds