A visualization of a sparse Mixture-of-Experts routing architecture with multiple expert paths and a gating network.

Build a Sparse MoE Router from Scratch in NumPy

A hands-on guide to implementing a sparse MoE router from scratch in NumPy, covering noisy top-k gating, capacity-factor batching, and auxiliary load-balancing loss — a CV-worthy side project for ML systems engineers.

September 11, 2026 · 14 min · 2810 words · martinuke0
PyTorch code and neural network architecture diagram

Building a Multi-Head Self-Attention Block with RoPE and ALiBi from Scratch

A hands-on guide to building a multi-head self-attention block with RoPE and ALiBi from scratch, signaling advanced ML and systems engineering skills to hiring managers.

September 10, 2026 · 9 min · 1903 words · martinuke0
A diagram of a neural network with attention branches

Build a Mini LLM Inference Engine with Tree-Attention Speculative Decoding

Learn to implement a compact LLM inference engine that showcases advanced systems skills, from KV cache reuse to tree-attention speculative decoding.

September 10, 2026 · 8 min · 1577 words · martinuke0
A Python script reading a GGUF binary file, with hex dump and tensor metadata visualization.

Building a GGUF Weight Loader from Scratch in Pure Python

A hands-on guide to building a zero-dependency GGUF weight loader from scratch in Python, covering the binary container format, tensor extraction, and a roadmap to production-grade features.

September 10, 2026 · 12 min · 2499 words · martinuke0
A schematic diagram of the safe. gateway architecture showing content flowing through policy checks, rate limiters, and audit log sinks.

Building 'safe.' — A User Safety Gateway That Signals Real Systems Skill

A hands-on guide to building ‘safe.’ — a User Safety Gateway that signals real systems engineering skill. Learn to implement policy-as-code content moderation, rate limiting, and audit pipelines with production-grade architecture patterns.

September 9, 2026 · 10 min · 2101 words · martinuke0
Feedback