HNSW vector index code illustration

Building a Production‑Ready HNSW Vector Index from Scratch

A complete, runnable Go implementation of HNSW with testing, benchmarking, and extension points — perfect for showing systems engineering chops.

November 1, 2026 · 7 min · 1421 words · martinuke0
Python code on a terminal displaying a GGUF weight loader

Pure Python GGUF Weight Loader: Streaming Quantized Tensors via Memory-Mapped Files

A step‑by‑step guide to building a pure Python GGUF weight loader that streams quantized tensors using memory‑mapped files, complete with code, testing, and production‑ready extensions.

October 12, 2026 · 8 min · 1680 words · martinuke0
A sleek notebook with code snippets and circuit diagrams, representing a differentiable MoE layer.

From‑Scratch Differentiable Sparse Mixture‑of‑Experts Gating Layer with Load Balancing in NumPy

A step‑by‑step guide to implementing a sparse Mixture‑of‑Experts gating layer in NumPy, demonstrating differentiable programming, load‑balancing, and production‑ready patterns for engineering roles.

October 5, 2026 · 9 min · 1796 words · martinuke0
Illustration of distributed gradient synchronization across nodes

Build a Distributed Data-Parallel Bucketed Gradient Synchronizer from Scratch

Learn how to implement a bucketed gradient synchronizer that reduces communication overhead in distributed training, perfect for a portfolio project that signals real systems engineering skill.

October 3, 2026 · 7 min · 1430 words · martinuke0
Illustration of a neural network attention pattern

Hands-On Build Guide: Flash Attention Implementation from Scratch in NumPy

A step-by-step NumPy guide to implementing Flash Attention with tiled multi-head self-attention and causal masking, perfect for a portfolio CV.

September 20, 2026 · 9 min · 1775 words · martinuke0
Feedback