“AI may not dream yet, but I’m definitely dreaming up some pretty exciting projects in the field!”
That spark of imagination drives my passion for Artificial Intelligence and Machine Learning, where I explore everything from large language models (LLMs) and Generative AI (GenAI) to reinforcement learning and human-machine interaction. Lately, I’ve been diving deep into cutting-edge areas like LLM Reasoning, Agentic AI, and Embodied AI. I’m actively engaging with these topics through research, coursework, and hands-on projects at UC San Diego. It’s an exciting time to be in AI, and I’m thrilled to be exploring these new areas!
Before joining UC San Diego, I spent five years at Samsung R&D Institute India - Bangalore (SRI-B), specializing in Machine Learning, Federated Learning, Edge Computing, and Android development. During this time, I led several impactful projects focused on improving user experience and privacy. As a Lead Engineer, I worked on edge-based personalization solutions using LLMs and developed a Python-based Android profiling tool to benchmark rendering performance. In Federated Learning, I pioneered privacy-preserving models for demographic prediction without compromising user data. I also designed and deployed machine learning models in resource-constrained environments, optimizing LLMs like FLAN-T5 to enhance user experience. Additionally, I developed Android applications for real-time ML inference, including solutions for boredom detection and next-app recommendations. My work involved collaborating with cross-functional teams to improve model accuracy and ensure smooth deployment across thousands of devices. These experiences refined my skills in distributed learning, performance optimization, and privacy-focused AI, leading to both patents and publications (see “Research Work” for details).
Before my time at SRI-B, I completed a summer internship at Hike Pvt. Ltd. in New Delhi (2017), where I developed an image classification model for the Hike Messaging app. During this internship, I gained hands-on experience with Convolutional Neural Networks (CNNs) and worked with tools such as Google ML Engine for cloud-based model training and TensorFlow Serving for local deployment. This internship sharpened my skills in machine learning, CNNs, and cloud technologies.
At IIT Kanpur, I worked on a variety of projects that furthered my technical expertise. I contributed to the Humanoid Project at the Robotics Club, focusing on Computer Vision and Speech Recognition modules. I also explored various machine learning domains, such as One-Shot Learning, Real-time Sentiment Analysis, and Question Similarity Detection. Additionally, I worked on more specialized projects like developing a Neural Network-based model for controlling a quadrotor. Another key project was implementing an n-body simulation using CUDA for parallel computing. These experiences deepened my knowledge of robotics, deep learning, and high-performance computing. For a full overview of my projects, check out the “Projects” section.
- Large Language Models (LLMs)
- Agentic AI
- Embodied AI
- Human-Machine Interaction
- Computer Vision
- Natural Language Processing (NLP)
- Reinforcement Learning (RL)
-
MS in Computer Science, 2024 - Present
University of California San Diego
-
B.Tech in Computer Science & Engineering, 2015 - 2019
Indian Institute of Technology Kanpur (IITK)
Experience
- Led the development of an automated Python-based Android profiling tool to benchmark rendering uniformly across devices, identifying bottlenecks (scroll janks) and enhancing rendering performance through improvements in the Android framework source.
- Led the development of four edge-based personalization LLM solutions, deriving actionable insights to enhance user experience.
- Fine-tuned the FLAN-T5 LLM model for our specific use-case, optimizing performance & achieving a ∼92% evaluation score.
- Collaborated with engineers and testers to improve the quality of ∼15k samples for one of the said personalization solution.
- Designed an edge ML solution to analyze phone usage data and detect boredom with ∼80% accuracy, enhancing user experience. Built an Android app for real-time inference with under 50ms latency, showcasing the model’s effectiveness.
- Pioneered a Federated Learning (FL)-based solution to predict gender and demographic age, enhancing privacy for ∼10k users. Explored innovative distributed learning techniques and tested diverse FL algorithms across 20+ input and model configurations, laying the groundwork for future privacy-preserving AI advancements.
- Developed the Robot Camera Visualization Android app for real-time visualization of depth maps and 3D point-clouds from a ToF camera at 30 FPS, with gesture-based UI features for enhanced user interaction, tailored to stakeholder requirements.
- Engineered a privacy-preserving edge ML solution for Next App Recommendation, published in IEEE ICSC 2022, by designing a memory-efficient model (99% size reduction) to minimize FL bandwidth costs. Trained and deployed the model in Java using DL4J, integrating it on Android edge devices with a User Trial (UT) app for training and inference across 500+ devices.
- Developed Neural Network (NN) model to predict the current location of a user based on their recent locations and time of the day
- Developed a simulation environment for replicating which cell tower in a given area a user would be connected to while in transit
- Developed an ML classification model to predict which cell tower a user is most likely connected to at any time of the day
- Top‐1 & Top‐3 prediction accuracies for the final model were 85‐90% and 90‐95% respectively on the evaluation dataset
- Implemented CNN models in Python using TensorFlow for image classification, leveraging Google ML Engine APIs to accelerate training on Google Cloud. Deployed the model with TensorFlow Serving to expose REST APIs for generating model predictions.
Research Work
Projects
