Build a BPE Tokenizer From Scratch in Pure Python
A hands-on build guide for a Byte Pair Encoding tokenizer in pure Python — complete with architecture diagrams, runnable code, testing strategy, and a senior-level extension roadmap.
A hands-on build guide for a Byte Pair Encoding tokenizer in pure Python — complete with architecture diagrams, runnable code, testing strategy, and a senior-level extension roadmap.
A practical guide to building a lazy checkpoint loader that memory-maps GGUF and safetensors files, parses tensor metadata, and dequantizes on demand.
A hands-on guide to building a mixture-of-experts router from scratch in Python, covering top-k gating, capacity factor scheduling, and load balancing loss — a CV-worthy project that signals real systems and ML engineering skill.
A step-by-step guide to building a real-time ML inference service with async processing, request batching, and observability — designed to demonstrate production systems engineering on your CV.
A hands-on build guide for a blockwise INT4 inference engine with packed-nibble weights, per-group scales/zero-points, and fused dequantizing GEMM — a portfolio project that demonstrates real systems and ML engineering depth.