Python

A conceptual diagram of paged KV cache blocks being allocated and managed in memory

Build a Paged KV Cache in Pure Python: A Portfolio Project That Signals Real Systems Skill

A hands-on guide to building a pure Python paged KV cache for transformer inference. This project demonstrates virtual-memory management, systems architecture, and deep learning engineering — exactly the skills hiring managers look for.

Build a Pure-Python GGUF and Safetensors Weight Loader

A hands-on guide to building a pure-Python gguf and safetensors weight loader from scratch. Parse binary headers, memory-map tensor data, and convert to numpy arrays for inference — with real runnable code and a roadmap to production-grade.

Illustration of a neural network training loop

Mini GPT Training Loop with Custom Autograd: A Hands-On Portfolio Project

A step‑by‑step guide to implement a tiny GPT training loop with custom autograd, perfect for a CV side project that showcases low‑level ML engineering skills.

Abstract illustration of a token stream passing through a draft and verification pipeline.

Speculative Decoding with a Draft N‑gram Model: A Pure‑Python Inference Engine

This project demonstrates end‑to‑end inference engineering, from language modeling to low‑latency token generation, and signals strong systems skills to hiring managers.

A visualization of paged KV cache memory blocks being swapped between CPU and GPU memory

Build a Paged KV Cache with Swapping for CPU-Only LLM Inference

A hands-on guide to building a paged KV cache with swapping for CPU-only LLM inference. Includes real, runnable Python code using PyTorch and demonstrates memory management patterns that signal senior-level systems skill.