This inventor holds 3 USPTO granted patents and 1 published patent application. Top assignees: Waymo LLC, Google Inc.. Active years: 2025-2026.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
Company Filing History:
Years Active: 2025-2026
Title: Jonathan James Mulligan and Machine-Learned User Interface Customization
Introduction
Jonathan James Mulligan is an inventor based in San Francisco, California, and works at Google Inc. His patent work includes a machine-learning approach to improving how user interface elements are selected for real-time content experiences.
Latest Patents
Mulligan is associated with 1 patent: “Training Pipeline for Training Machine-Learned User Interface Customization Models.” The patent describes a method that analyzes data from user sessions, including interactions with interface elements and requests for related resources. A first machine-learned model estimates the incremental probability of a request when an input element is displayed. Those estimates are then used to update a second model, which optimizes candidate proposals for selecting elements to populate a user interface during real-time content selection.
Career Highlights
The patent reflects work at the intersection of machine learning, user interface customization, and real-time content selection. Its training pipeline uses observed user-session data to guide model updates and improve the selection of interface elements.
Collaborations
Mulligan’s listed coworkers include Lisa Michelle Jakobovits and Mert Dikmen. The patent information provided does not specify their roles or contributions to this invention.
Conclusion
Jonathan James Mulligan’s patent describes a data-driven pipeline for training models that help customize user interfaces, connecting user-session analysis with real-time selection of interface elements.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

