San Francisco, California, United States
I am currently a machine learning engineer on the content understanding team at Meta working on foundational vision and multimodal models. Previously, I was a machine learning engineer on the Perception team at Lyft Level 5 working on computer vision models for self driving. Before Lyft I was a Masters student at the University of Waterloo. For my research I focused on computer vision and deep learning, specializing in visual perception and scene understanding. The goal of my research is to combine different visual perceptions in order to produce a rich scene understanding, while maintaining a balance between speed, accuracy and size for operational AI.
AI Content Understanding
Worked on computer vision for autonomous driving.
Developed an Artificial Intelligence powered assistant to help those with visual impairment, as well as older adults.
Worked on monocular depth estimation for the Level 5 Autonomy / Perception team.