Build a GGUF Parser and Safetensors Loader: A From-Scratch Mmap-Backed Weight Inspector
Build a from-scratch GGUF parser and safetensors loader that memory-maps tensor data straight into numpy, with integrity checks you can drop on a CV.
Posts
Building a FlashAttention-2 Forward Kernel in Pure NumPy
TL;DR — FlashAttention-2 is an IO-aware attention algorithm that fuses the softmax and matrix multiply into tiled CUDA kernels. We rebuild the forward pass from scratch in pure NumPy: blocking the QKV matrices into tiles, running a streaming softmax per block, and rescaling outputs online. The result is a runnable, testable side project that demonstrates memory-hierarchy thinking, numerical stability, and GPU-style programming patterns — exactly what hiring managers look for on a CV. ...
Optimizing Redis with Client-Side Caching and the RESP3 Protocol
A practical look at how the RESP3 protocol and client-side caching let Redis clients invalidate entries locally, eliminating round trips and shaving milliseconds off tail latency.
Build a Mixture-of-Experts Router From Scratch in PyTorch
A portfolio-grade project: a pure PyTorch mixture-of-experts router with top-k gating, expert load-balancing loss, and Switch-style capacity factors — with runnable code, tests, and a roadmap to senior-level extensions.
Build a Speculative Decoder From Scratch: A Portfolio Project That Signals Real Systems Skill
A working engineer’s guide to implementing a speculative decoder from scratch: draft with n-gram proposals, verify with a target model, ship it as a portfolio piece. Real code, real benchmarks, real extensions.