All work

TopicLens

Sorts anything you have read or written into topics, live, on the Mac's Neural Engine. Nothing leaves the machine.

On-device machine learningShipped for personal use474 items/s, purity 0.93

About 474 items per second end to end on an M4

Problem
Big personal text collections are hard to browse by theme without sending them to a cloud model.
My role
Builder: clustering, topic naming and search on top of an on-device embedding model, plus the Mac app, CLI and eval harness.
Shipped
Native Mac app and CLI.
Stack
  • Swift
  • SwiftUI
  • Core ML
  • EmbeddingGemma on the Apple Neural Engine
Outcome
  • Topic purity 0.93 on 10,080 labelled posts
  • Search precision at 10 of 0.85

About me

Wilfredo Baez

Hi, I'm Wilfredo. I'm an AI product engineer in New York, building the products I want to use, and the systems that help me build them.

I work the way a lead works with a team. I decide what to build, write the spec, and direct AI coding agents through small changes I can review. Nothing is accepted on trust: every project here has a test gate, and anything that sends, publishes, pays or deletes waits for my approval.

Before this I spent years on the support side of tech at Apple and Geek Squad, provisioning devices at volume and fixing whatever people brought in. I still run Elevare Solutions, a small studio that builds websites and tools for local businesses. That is where I learned to listen to the people who use what I build.

I'm looking for a founding or early engineering role where I can own a product from its first useful version onward.

WilfredoNew York

Email meLinkedInResume