Portfolio Project

A laptop displaying code for LoRA adapter training

Build a LoRA Adapter Trainer from Scratch in Pure Python

Learn to implement LoRA fine-tuning from scratch, creating a portfolio project that demonstrates real ML infrastructure expertise.

A diagram of a mixture-of-experts router

Build Your Own Mixture-of-Experts Router with Top‑k Gating

This tutorial walks you through building a top‑k gated mixture-of-experts router in PyTorch, giving you a concrete portfolio piece that demonstrates model architecture, sparse routing, and system‑level scaling.

A visualization of low-rank matrix decomposition applied to transformer weight matrices

Build a LoRA Adapter Trainer from Scratch: A Portfolio Project That Signals Real Systems Skill

A hands-on build guide for a from-scratch LoRA adapter trainer featuring gradient checkpointing and low-rank matrix fusion in pure Python, with architecture breakdown, runnable code, and a senior-level extension roadmap.

A code editor displaying NumPy matrix operations alongside a visualization of low-rank decomposition

Build a LoRA Fine-Tuning Engine from Scratch in Pure NumPy

A hands-on guide to building a LoRA fine-tuning engine entirely in NumPy, covering low-rank decomposition, gradient computation, and adapter updates with zero deep-learning framework dependencies.

Build a GGUF Parser and mmap-Based Tensor Loader: A Portfolio Project That Signals Real Systems Skill

Build a production-grade GGUF parser and mmap-based tensor loader with quantized dequantization and safetensors conversion. This hands-on guide shows real code, architecture decisions, and a roadmap from toy to production.