Python

A diagram of a context window manager pruning tokens.

Memory‑Efficient Context Window Manager with Attention‑Guided Token Pruning

This project delivers a runnable Python library that compresses LLM context windows by scoring token importance with attention and dropping low‑impact tokens, demonstrating practical systems and ML engineering.

A conceptual diagram of speculative decoding showing a fast draft model feeding tokens to a larger verifier model.

Build a Speculative Decoding Engine: A Portfolio Project That Signals Real Systems Skill

A hands-on guide to building a speculative decoding engine with a draft model and verifier in pure Python. This project signals deep systems expertise and is practical enough to actually complete, with real runnable code at every step.

Hands‑On Build Guide: Pure‑Python Safetensors Parser & Weight Shard Assembler with mmap Lazy Loading

A step‑by‑step guide to creating a lightweight, mmap‑based safetensors parser you can ship, test, and extend for real‑world model serving.

A visualization of memory blocks and tokens in a neural network inference engine

Building a Mini LLM Inference Engine in Pure Python

A hands-on guide to building a mini LLM inference engine featuring PagedAttention and advanced KV cache management, designed to demonstrate production-grade systems architecture on your CV.

A dashboard showing a RAG system answering questions

Build an End-to-End RAG System for Your Portfolio

Learn to build a production-style RAG pipeline that demonstrates end-to-end systems engineering, from data ingestion to API serving.