James Hu
Building ML-driven AI systems focused on orchestration and architecture.
Featured Work
Projects
These projects reflect my interest in building systems that integrate models, data, and infrastructure into reliable software.
Ai Engineering Book
A technical book for engineers building production LLM applications — from Python and ML foundations through RAG, agents, deployment, and Staff+ system design. Authored in Quarto, hosted at book.jameshu.io.
Multi Tenant Backend Api
Django REST API that evolved from a single-tenant portfolio backend into a multi-tenant architecture with custom managers, tenant isolation, and AWS deployment.
From the Blog
Latest Articles
Writing on system design, ML systems, and building production-grade software.
How to Think About AI Agents
A working mental model for agents — and when not to build one. A companion to Chapter 8 of my book, AI Engineering.
RAG Is an Architecture, Not a Feature
Why retrieval-augmented generation is a system you design, not a library you import — a companion to Chapter 7 of my book, AI Engineering.
Building Your First LLM Application
The gap between calling an API and shipping an app — a companion to Chapter 4 of my book, AI Engineering.
Neural Networks Got Too Big to Read - Now We Sequence Them
Why large language models stopped reminding me of software and started reminding me of genomics — and what that says about studying any system too large to read.