About me

I am currently pursuing a Master of Science in Computer Vision at Carnegie Mellon University (CMU). I have previously completed a Bachelor of Technology (Honours) in Computer Science and Engineering from the International Institute of Information Technology - Hyderabad (IIIT-H).

Broadly, my research and academic interests lie in Computer Vision and Machine Learning. My long term goal is to work on complex systems that match and surpass human vision in processing visual information in all aspects such as object detection, recognition, semantic understanding, 3D understanding, etc. I envision systems that can extract all relevant information from visual inputs, contextualize this information and use it in combination with other modalities to make appropriate inferences and decisions. Within Vision, I am particularly passionate to work on 3D reconstruction, implicit representations and the intersection of 2D and 3D information processing. I am also keen to explore the domain of generative models with a focus on the recent advances made with stable diffusion models. In pursuit of my interests, I am currently searching for full-time job opportunities starting from the Spring of 2025. Feel free to reach out to me with any such opportunities or even just to have a stimulating discussion on my work and/or recent trends in the fields mentioned above.

What i'm doing

  • computer vision icon

    Computer Vision

    I keep up-to-date on the latest trends in the domain of Computer Vision and am currently involved in a couple of projects on the 3D Vision and Generative Vision side.

  • machine learning icon

    Machine Learning

    I dabble in and keep an eye on the most recent developments in Machine and Deep Learning and time-to-time participate in courses and smaller projects in these fields.

  • research icon

    Research

    I love participating in research projects in domains of my interest and am always involved in at least one such project. I am looking to try my hand at research in the industrial setting as it is more grounded in terms of feasibility and one can see the impact of their work directly.

Resume

Experience

Experience

  1. Robotics Software Intern - Robotics Perception

    May 2024 — Aug 2024

    NVIDIA

    1. Enhanced the performance of the ESS 4.0 stereo perception model with better data (real data), more diverse augmentations, and architectural experiments. Improvements have since been integrated into the pipeline and will be part of ESS 4.1.
    2. Boosted training time by 10x with distributed training and explored alternate evaluation methods to better quantify model performance.

  2. Teaching Assistant

    Aug 2022 — Dec 2022

    IIIT-H
    Mobile Robotics
    One of three teaching assistants overseeing the Mobile Robotics course with a strength of 33 students. Conducted a couple of lectures and tutorials in person during the course. Other responsibilities included setting papers, grading papers, conducting evaluations, addressing student doubts and issues, updating the course website with the required documents, etc.

  3. Teaching Assistant

    Oct 2021 — Dec 2021

    IIIT-H
    Automata Theory
    One of eight teaching assistants overseeing the Automata Theory course with a strength of 212 students. Conducted a couple of online tutorials during the course. Other responsibilities included setting papers, grading papers, conducting evaluations, addressing student doubts and issues, updating the course website with the required documents, etc.

  4. Software Engineer Intern

    May 2021 — Jul 2021

    Virtual Labs
    Designed an experiment template in HTML, CSS, and JavaScript for reuse by other developers and built 10 experiments of the Soil Mechanics Lab which became the third-most viewed IIIT-H lab for the past 2 years with 1.2 million views.
    Developed a plugin from scratch in JavaScript and Handlebars to help experiment developers fix major bottlenecks in various SEO aspects using Google’s Lighthouse API.
    Modified the experiment build script to add plugin processing capabilities.
    Prior to the internship, as part of a course project (DASS), I led a four-member team to build all 10 experiments of the Structural Dynamics Lab of which I built 4.

Education

  1. Carnegie Mellon University

    2023 — 2024

    Master of Science in Computer Vision
    CGPA: 4.17 / 4.00
    Courses: Advanced Computer Vision, Deep Learning Systems, Multimodal Machine Learning, Learning for 3D Vision

  2. International Institute of Information Technology Hyderabad

    2019 — 2023

    Bachelor of Technology (Honours) in Computer Science and Engineering
    CGPA: 9.12 / 10.00
    Courses: Machine Data and Learning, Digital Image Processing, Mobile Robotics, Computer Vision, Statistical Methods in AI

Projects

Contact

Contact Form