About Me

I am Blake Guo, an AI and platform engineer focused on building practical, production-grade systems for machine learning, language models, and data-intensive applications.

My work sits at the intersection of ML platforms, retrieval and agent systems, large-scale data infrastructure, distributed services, and cloud-native engineering. I have built platforms inside large engineering organizations, founded AI products from zero to paid adoption, and worked across the full stack from model workflows to backend systems and user-facing applications.

How I Think About Systems

I have a PhD in Information Science with research roots in data mining and distributed algorithms. That background still shapes how I think about systems: start from the data, understand the constraints, and design for reliability under real production load.

• ML/AI systems
• LLM applications
• retrieval and evaluation
• data infrastructure
• distributed systems
• cloud services
• reliability

What This Site Is For

This site is where I turn technical learning into durable writing: concise explanations, engineering tradeoffs, implementation details, and ideas worth revisiting.

The writing is centered on ML/AI, distributed systems, and data infrastructure: how production AI applications are assembled, how data moves through reliable platforms, and how engineering decisions hold up under real constraints. I may also write about interesting AI startups worth studying. The goal is to make ongoing work, reading, and experimentation precise enough to become useful later: as references, as implementation notes, and as a record of how my thinking evolves.

For questions, corrections, or technical discussion, GitHub Issues is the best place to reach me.