M.S. in Computer Science
University of California San Diego
Jun 2019
La Jolla, CA
-
GPA: 3.96/4.00
-
Specialization: Artificial Intelligence
B.Engg. (honors) in Electrical and Electronics Engineering
Birla Institute of Technology and Science (BITS Pilani)
Jun 2015
Pilani, India
-
GPA: 9.23/10.00
-
Graduated with distinction and among top 5%
Online Courses
-
Self Driving Car Nanodegree, Udacity
-
Artificial Intelligence Nanodegree, Udacity
-
Data Science at Scale Specialization, University of Washington, Coursera
Sr. Machine Learning Engineer
Twitter Inc.
Nov 2021 - Present
Seattle, WA
Usual works involves collaborating with different product teams to train and deploy model that incorporates content-based signals, mentor and guide team members, and look out for new product improvement opportunities. Working on improving user-tweet recommendation, search relevance, and generic model serving infrastructure.
Machine Learning Engineer -II
Twitter Inc.
Aug 2019 - Nov 2021
San Francisco, CA / Seattle, WA
Worked with different product teams to improve product metrics for user-user recommendation, tweet-tweet recommendation, and user-tweet recommendation using Model-Based Candidate Generation (MBCG) and ANN.
Graduate Student Researcher / Graduate Student Assistant
University of California San Diego
Oct 2017 - Jun 2019
La Jolla, CA
Performed extensive literature review and designed and documented a generic vision-based architecture for autonomous driving vehicle in form of a thesis. Also, served as a teaching assistant for various courses in data science and machine learning.
Software Engineering Intern
Twitter Inc. (employed by Pro Unlimited
Jun 2018 - Sep 2018
San Francisco, CA
Worked with Cortex - the team behind Machine Learning Infrastructure at Twitter - to obtain representation of tweets based on its content. Worked on low memory footprint models to enable on-device machine learning inference capabilities.
Data Scientist
Media IQ Digital
Feb 2016 - Aug 2017
Bengaluru, India
Developed predictive and behavorial user models for ad recommendation. Also, designed and developed optimized query engine for churning petabytes of data. Proposed and developed a poof-of-concept for a privacy-focused cookieless architecture for behavorial ad targeting.
Application Developer
Oracle, Bengaluru, India
Jun 2015 - Feb 2016
Bengaluru, India
Developed application to cleanse geographical datasets to get rid of typographical errors and duplicate records using phonetic algorithm. Worked on development of MVVC framework with focus on client-side dynamic HTML node.
Intern, , Nagpur
Globallogic India Pvt. Ltd.
Jan 2015 - Jun 2015
Nagpur, India
Worked for one of the world’s top medical device companies. Developed image processing libraries for enhancement and segmentation of biomedical imaging and optimized them to run on mobile devices. Also, developed APIs to create animated views for bar/area/line charts for Android Platform.
Mitacs Globalink Research Intern
Globallogic India Pvt. Ltd.
May 2014 - Aug 2014
Nagpur, India
Worked on development of 3D Immersive Cognitive Exercises for patients of Alzheimer and Dementia patients (using Oculus Rift Development Kit) for spatial capability assessment of humans. Implemented logic to make 3D World from 2D SLAM Map. Proposed, designed, and developed a new collision detection module for the Game Engine.. Proposed, designed, and developed a new collision detection Mmdule for the Game Engine.
Teaching Assistant
Birla Institute of Technology and Science, Pilani (BITS Pilani)
Jan 2014 - Dec 2014
Pilani, India
Helped with preparing course material and lectures and conducted regular lab sessions for course on Microprocessor - Interfacing and Programming (x86 architecture and assembly language) and Analog and Digital VLSI Design.
Project Trainee
Bhabha Atomic Research Center (B.A.R.C.)
May 2013 - Jul 2013
Mumbai, India
Implemented a simulator demonstrating effect of reactivity control rod’s height on nuclear power generated based on Point Kinetic Equation (set of nonlinear differential equations), and designed and implemented Data Acquisition System (DAS) for the simulator.
Lessons Learned addressing Dataset Bias in Model-Based Candidate Generation at Twitter
KDD (San Diego, CA, August 2020)
-
Explore the dynamics of the dataset bias problem and then demonstrate how to use random sampling techniques to mitigate it
-
Finally, in a novel application of fine-tuning, we show performance gains when applying our candidate generation system to Twitter's home timeline
Lessons learned from deploying autonomous vehicles at UC San Diego
Field and Service Robotics (Tokyo, JP, August 2019)
-
Discussed brief overview of the overall design and the design decisions for construction of vehicles for last-mile delivery
-
Discussed design and challenges of vehicles for the micro-mobility challenge based on open source Autoware system
-
Proposed requirements for roboust systems that include a robust control design, a shift towards increased use of image data over LiDAR data, handling of a richer set of vehicles / pedestrians in a last mile scenario, and overall system characterization and evaluation
Vision-based Autonomous Driving
Master's Thesis (UC San Diego, June 2019)
-
Considering the drawbacks of the LiDARs, the availability of an alternate solution, and the recent progress of computer vision techniques in the last few years, proposed an architecture for vision-based autonomous driving.
-
Outlined building blocks for the development of this vision-based architecture and described functionality of these blocks. Additionally, provided a brief overview of existing studies and research to implement these blocks.
-
Furthermore, we discuss the design and implementation of a few of these blocks in the purview of the activities being undertaken at Autonomous Living Laboratory (AVL) at UC San Diego.
Transfer of Expertise in Deep Neural Networks
VSS, Tampa FL, May 2019
-
Studied the attention map of expert and novice birdwatchers by modeling them as deep neural network (VGG-16) (experts is defined as systems that categorize stimuli at a subordinate level, and novices are defined as systems that categorize the same stimuli at a coarser grain)
-
The attention map used by the expert network has higher entropy, and smaller, local features than the novice networks (suggesting that the expert looks at multiple locations to make a classification decision)
-
The attention map used by the expert can be used to train the novice, resulting in faster training and better performance. This to be analogous to the expert telling the novice where to look for discriminative regions of the image
Applications of Deep Learning to Autonomous Vehicles
International Conference on Business Analytics and Intelligence, IIM Bangalore, Dec. 2017
-
Explored some of the feature selection and preprocessing techniques to make deep learning models robust
-
Presented a Deep Learning based approach to perform various tasks like traffic sign classification, object detection, semantic segmentation and lane detection
-
Explored the techniques in Deep Learning that are currently being used in the industry for the successful navigation of autonomous vehicles
Electronics Aid for Elder and Sick
Recent Advances and Innovations in Engineering, IEEE, Poornima University, Jaipur, May 2014
-
Proposed a wireless switch board for easy-accessibility in an hospital-like environment for controlling various electrical appliances like light, fan, etc. without interference with similar wireless switches in adjoining room
-
The data signal is communicated to receiver wirelessly by IR Remote Controller. The receiver consists of IR Receiver, TSOP1838, to read data signal operating at 38 kHz and a microcontroller to process data and communicate trigger signal to change the state of switch
