Hierarchical Navigable Small World Vector Index: A Hands‑On Portfolio Project
A step‑by‑step guide to building a hierarchical navigable small‑world vector index from scratch, with runnable code, benchmarking, and production‑ready extensions.
Systems
Building a Sliding Window Attention Block from Scratch: A Portfolio Project for Systems Engineers
Implement a sliding‑window attention block in PyTorch, test it, and extend it with distributed training, mixed precision, and monitoring to showcase systems expertise.
Hands‑on build of a pure‑Python BPE tokenizer with Huffman merge tree, live visualizer, and tiny LM demo—great for showcasing systems skills
A practical, pure‑Python BPE tokenizer with a Huffman‑coded merge tree, live visualizer, and character‑level LM demo that highlights systems engineering skills.
Hands-On Build Guide: PagedAttention KV Cache Manager with Block Allocation and Copy-on-Write in Pure Python
A step‑by‑step guide to implementing a paged‑attention cache, complete with block allocation, COW, and testing, so you can showcase real systems skills on your CV.
Building a GGUF Parser with Memory-Mapped Lazy Tensor Loading in Pure Python
A hands-on guide to building a pure-Python GGUF parser that lazily memory-maps tensors and decompresses quantized blocks on demand, demonstrating deep systems knowledge.