I’m a Research Engineer at Tesla AI, Mountain View. Before that, I was a PhD candidate at the CLIC, University of Oxford, supervised by Prof. Alice Turing and Prof. Charles Babbage.

My dissertation work concentrates on utilizing auditory information to resolve ambiguities and develop representations across modalities. My broader interests encompass: audio/speech recognition, audio to text transcription, and cross-modal representation learning.

In 2019, I interned at Google DeepMind with Naomi Saphra and Sam Bowman, where I worked on creating immersive audio narratives. During the summer of 2017, I interned at IBM Research Watson, collaborating with Susan Hendricks on developing speech recognition systems for hearing-impaired individuals.

Prior to my PhD, I earned my master’s degree from the Department of Informatics and Communications, University of Toronto as a part of the Global Communications Technologies Program, under the guidance of Prof. Graeme Hirst. I received my undergraduate degree from NIT Trichy, majoring in Machine Learning, in association with the Center for Artificial Intelligence and Robotics.