I am currently a Senior Research Engineer in the Perception team at Qualcomm AI Research, where I focus on developing foundational models and techniques to enhance the efficiency of existing models, with applications in Generative AI and 3D vision. As part of the Perception team, I have published research in top-tier computer vision and machine learning conferences and workshops. I have significant experience of building and evaluating foundational models that can handle a wide range of vision applications like 3D object detection, 2D and 3D segmentation and depth estimation.
Prior to this, I graduated with a MS in CSE at UC San Diego. At UCSD, I worked with Prof. Kamalika Chaudhuri on online learning and with Prof. Rose Yu on a project aimed at unsupervised relational inference in dynamically changing systems. I am interested in both the theoretical and applied aspects of machine learning. I am particularly excited about the applications of machine learning in dynamically evolving systems. In the past, I was a Research Fellow at Microsoft Research working on graph representation learning in the Applied Machine Learning group.
At UCSD, my coursework involved working on applications of Machine Learning in areas like Computer Vision and Natural Language Processing. I have also taken many theoretical courses in machine learning in order to understand the theoretical aspects of the area. Throughout my Machine Learning projects, I have extensively used PyTorch and TensorFlow. I am also well versed with C/C++ and Golang.
I earned my Bachelors degree in Computer Science from IIT Varanasi where I worked on image captioning models for limited paired image-caption data for my bachelors thesis. I was ranked 3rd in the graduating batch of CSE department during my undergrad.
Google Scholar |