I am an AI researcher at Meta FAIR, working on applying deep learning to scientific problems.
My focus over the last few years has been on using AI to discover new catalysts for use in renewable energy storage as part of the Open Catalyst Project (OCP). As we increase our reliance on renewable energy sources such as wind and solar, which produce intermittent power, storage is needed to transfer power from times of peak generation to peak demand. A possible solution that can scale to nation-sized grids is to use excess energy to create other fuels. To be widely adopted, we need to discover new electrocatalysts to synthesize these fuels in a cost effective manner. While quantum mechanical simulations can be used to test new catalyst structures, the high computational cost of these simulations limits the number of materials that can be tested. As part of this project, we are developing new methods for finding effective catalysts by using Machine Learning to efficiently approximate these calculations.
Previously, I had worked on accelerating MRI scans using deep learning as part of the fasMRI project. Accelerating MRI scans by taking fewer measurements has the potential to reduce medical costs, minimize stress to patients and make MRIs more accessible. As part of this project, we developed new machine learning methods to accelerate MRIs by over 4x and validated them clinically.
Prior to joining Meta, I worked as a Senior Research Scientist at Baidu Silicon Valley AI Lab with Andrew Ng on speech recognition, where I was part of the team that developed the Deep Speech 2 model. Prior to Baidu, I worked as an AI Engineer at Twitter, building online ML pipelines for ad ranking and targeting.
I have a Masters in Language Technologies from the Language Technologies Institute at Carnegie Mellon University, where I worked with Prof. Roni Rosenfeld on modeling the spread of infectious diseases using machine learning and agent based modeling as part of the FRED project.