Python

Abstract representation of a graph of vectors

Building a HNSW Vector Index from Scratch in Python

This guide walks you through building a hierarchical navigable small world vector index in pure Python. You’ll learn brute‑force construction, greedy graph search, and how to extend it for production.

Building a BPE Tokenizer from Scratch in Pure Python

A hands‑on guide to implementing a byte‑pair encoding tokenizer in pure Python, covering vocabulary learning, encode/decode, and merge‑based subword segmentation.

Code editor showing a tokenizer implementation with merge queue diagrams

Build a Streaming Byte-Level BPE Tokenizer: A Portfolio Project That Signals Real Systems Skill

A hands-on build guide for a streaming byte-level BPE tokenizer with persistent merge queues, atomic byte-loss tracking, and reversible byte fallback for arbitrary Unicode.

Building a Paged KV Cache Allocator with Continuous Batching in Pure Python

This project demonstrates memory management, concurrent request scheduling, and low-level allocator design—all core skills for backend and ML infrastructure roles.

A visualization of paged attention memory blocks arranged in a cache hierarchy with eviction pointers

Build a Paged Attention KV-Cache Manager with LRU Eviction in Pure Python

A hands-on build guide for a paged attention KV-cache manager with LRU eviction in pure Python — a portfolio project that demonstrates LLM inference systems knowledge and signals senior-level engineering capability.