Guided the front-end team for Lobe, a project incubated in the Office of the CTO aimed at democratizing machine learning.
Lobe is a free, easy-to-use desktop application that has everything you need to bring your machine learning ideas to life. Just show it examples of what you want it to learn, and it automatically trains a custom machine learning model that can be shipped in your app.
I led the migration of the Lobe web application and services from cloud infrastructure to a desktop application built on Electron — pivotal to shipping Lobe as a free offering — and built highly interactive, real-time UX for model training, evaluation, and management. I later guided the team to public release and its graduation from incubation into the Microsoft Power Platform organization.
Focus
Building a fluid, visually-driven desktop application using web technologies that hid the immense complexity of model training behind a beautiful, accessible interface.