PyTorch

Diagram of gating network routing to experts

From Scratch: Sparse Mixture-of-Experts Router in PyTorch

This project implements a sparse mixture-of-experts router with learned gating and top-k expert selection, demonstrating practical deep learning systems skills.

A developer typing code with a neural network diagram in the background.

Build a LoRA Adapter from Scratch in PyTorch

Learn to code a LoRA adapter from scratch in PyTorch, enabling efficient transformer fine‑tuning and a standout CV project for engineering roles.

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 diagram of the embedding adapter architecture.

Building a Self-Supervised Embedding Adapter for Arbitrary Vectors

Learn to build a self-supervised adapter that maps any embedding to a similarity-preserving space, with production-ready PyTorch code.

A sleek neural network diagram overlaid on a laptop screen

Build Your Own Fused Low‑Rank LoRA Fine‑Tuning Engine From Scratch

A hands‑on guide to building a fused low‑rank LoRA fine‑tuning engine from scratch, with runnable PyTorch code, architecture diagrams, and production‑ready extensions.