Machine Learning Infrastructure

A visualization of a hierarchical navigable small world graph with layered nodes and weighted edges

Build an HNSW Vector Index from Scratch in Pure Python

A hands-on build guide for a pure Python HNSW vector index — the data structure powering billion-scale vector search at Meta, Spotify, and Qdrant. Includes runnable code, architecture diagrams, and a senior-level extension roadmap.

Code editor showing Python vector quantization implementation

Build a Pure Python IVF Index with Product Quantization and Residual Vector Quantization

A hands-on guide to building a pure Python IVF index with product quantization and residual vector quantization — a portfolio project that signals deep systems and ML infrastructure skill to hiring managers.

Code editor showing a Python implementation of flash attention with tiling and online softmax in NumPy.

Building Flash Attention from Scratch in Pure NumPy: A CV-Worthy Systems Project

Build flash attention from scratch in pure NumPy using tiling and the online softmax trick, then extend it toward production. A deep, runnable project that signals real systems engineering to hiring managers.