Python

A schematic of a mixture-of-experts model routing tokens to experts.

Build a Minimal Mixture-of-Experts Inference Engine in Pure Python

Implement a minimal mixture-of-experts inference engine from scratch in Python, demonstrating systems thinking, custom loss functions, and production-ready patterns.

A distributed task queue architecture diagram showing clients, a broker, and multiple worker nodes processing jobs.

Build a Distributed Task Queue from Scratch: A Portfolio Project That Signals Real Systems Skill

A hands-on build guide for a distributed task queue side project that demonstrates concurrency, persistence, and distributed systems skills — with real, runnable code and a clear roadmap to production-grade complexity.

A conceptual diagram of a user safety pipeline with input validation, classification, rule engine, and alerting stages.

User Safety: safe — A Hands-On Build Guide for a Portfolio-Worthy Systems Project

A hands-on guide to building ‘safe’, a real-time user safety engine that classifies content, applies configurable rules, and flags violations — demonstrating systems architecture, ML integration, and production-grade engineering.

Sliding-window attention KV cache concept

Building a Sliding-Window Attention KV Cache with Dynamic Token Pruning

This guide walks through implementing a sliding-window attention KV cache with dynamic token pruning, providing runnable Python code and tests.

Python code and matrix multiplication diagrams on a dark terminal screen.

Build a FlashAttention-2 Inference Kernel from Scratch in Pure Python

Learn how to build a FlashAttention-2 inference kernel from scratch in pure Python. This guide covers tiled block-sparse causal attention and fused softmax to signal deep systems engineering skills.