Machine-Learning

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.

Diagram of grouped-query attention with rotary position embeddings feeding into a tiled Flash-Attention forward pass.

Building Grouped-Query Attention with RoPE and Flash-Attention from Scratch

Step-by-step tutorial for implementing GQA, RoPE, and an online-softmax Flash-Attention forward pass in pure PyTorch — a portfolio project that signals real systems-level ML skill.

Diagram of a streaming attention engine processing tokens through a sliding window with KV-cache reuse.

Building a Streaming Sliding-Window Attention Engine in Pure Python

A portfolio-grade systems project that demystifies LLM inference by implementing streaming sliding-window attention, prefix KV-cache reuse, and dynamic context eviction from scratch in pure Python.

Neural network diagram with attention heads visualized as colored connections between token nodes.

Building LLMs from Scratch: A Working Engineer's Guide

A working engineer’s end-to-end guide to assembling a transformer language model in PyTorch: from BPE tokenization to multi-head attention, rotary embeddings, and a real training loop on a single GPU.

Diagram of an LLM agent loop connecting perception, planning, tool use, and memory

Agentic AI in 2026: What Stanford's Overview Actually Means for Working Engineers

Stanford’s agentic AI overview offers a clean taxonomy, but production engineers need to know how the four-agent model, tool-use loops, and memory architectures translate into deployed systems — and where they fall apart.