Deep Learning

A code editor showing a Python implementation of a transformer attention block with mathematical notation in the background.

Build a Transformer Self-Attention Block from Scratch in Pure Python

A hands-on guide to implementing a transformer self-attention block from scratch in pure Python, covering rotary positional embeddings, causal masking, and grouped-query attention — with real, runnable code and a roadmap to production-grade extensions.

A circuit board with a neural network diagram

Building a Production-Grade Model Quantizer for Your Portfolio

A step-by-step guide to building a model quantizer that shrinks neural networks for edge deployment, demonstrating systems engineering skills to recruiters.

A directed acyclic graph with nodes representing operations and edges representing gradients flowing backward.

Backpropagation Demystified: How Neural Networks Actually Learn

Backpropagation is just the chain rule applied to a computational graph. Here’s how it works, why it scales, and how modern frameworks hide the math so you can focus on shipping models.

Stylized diagram of GPU memory blocks being cached and reused across allocations.

Optimizing GPU Memory Pools: Inside PyTorch's CUDA Caching Allocator

PyTorch’s CUDA caching allocator hides the cost of repeated allocations by recycling VRAM in fixed-size blocks. Here’s how it works, why it matters at scale, and how to squeeze more performance out of it.

Diagram of a transformer training loop showing activations dropped at checkpoint boundaries and recomputed during backward pass.

Building a Gradient Checkpointing Memory Scheduler From Scratch: A Portfolio Project That Actually Signals ML Systems Skill

A practical build guide for a portfolio-grade gradient checkpointing scheduler that trades compute for memory in mini GPT training. Includes runnable PyTorch code, a scheduler design, tests, and a roadmap to production-flavored upgrades.