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

TopicLens on the Mac sorting a 10,080-post demo stream into eight topics on the Neural Engine, each post tagged with its topic.
The Mac app on its synthetic 10,080-post demo stream, sorting live on the Neural Engine, captured November 2026.
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. My degree is in biology, but I kept getting pulled toward technology I could build with.

Before engineering I was deep in AI and crypto, and I ran my own digital magazine. It taught me to learn new tools fast and to make things for real readers.

Then I made the move into AI engineering. I direct AI coding agents the way a lead directs a team: I write the spec, review small changes, and accept nothing on trust. Every build here has a test gate, and anything that sends, publishes, pays or deletes waits for my approval.

Along the way I worked tech support at Apple and Geek Squad, and I run Elevare Solutions, a small studio that builds websites and tools for local businesses.

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

14 builds2,100+ tests written4 live

WilfredoNew York

Email meLinkedInResume