cv

Importance Sampling Based Federated Unsupervised Representation Learning

IEEE

Published work on a novel FL algorithm for unsupervised and personalized representation learning.

Software Engineer

Microsoft

Building impactful APIs for Microsoft Graph Teams, specializing in meetings, teams, and channels. Developed a CI/CD pipeline for a Business Intelligence data pipeline.

• Delivered Teams Graph APIs for Meetings, Teams & Channels with 200K+ monthly calls; adopted by key enterprise partners.
• Built a Bulk Remove API with IC3 async support, eliminating 47.5% request throttling.
• Enhanced Transcript & Recording APIs with metadata to enable duration estimation and traceability.
• Engineered telemetry and deployment pipelines to track 1B+ monthly calls and 10% MoM growth.
• Created BI Dashboards in Azure Data Explorer; streamlined BI reporting and surfaced monetization insights for leadership.
• Finalist at Microsoft FHL Hackathon, built an MCP server; Planner assistant using Graph change notifications to generate personalized to-do lists using chats, channel messages and meeting transcripts in Teams.

Software Engineer Intern

Microsoft

Worked on ECS flighting system for Audio, Signal and MediaTA under OneDrive SharePoint.

• Implemented Killswitch support in Signals microservice using ECS flighting, developed and tested a flexible ECS framework for typed values, enabling safe and continuous deployments.
• Developed a private preview pipeline for ZTNA, filtering tenant Signals via ECS and transmitting serialized data to EventHub.

Deep Learning Android Game Developer

Atletik Games

Developed Android games based on deep learning for Physical Education during Covid-19 lockdown.

• Integrated state-of-the-art pose and object detection models
• Deployed games to 3 schools with 500+ students

Research Project

SeekSuspect

• SeekSuspect is an interactive facial image retrieval model that uses visual memory as input to retrieve faces from a large-scale database.
• Fine-tuned pre-trained ResNet and VGG-16 models, improving accuracy from 82% to 86% by enhancing efficiency and embedding extraction.
• Evaluated and compared various clustering algorithms for embedding extraction, improving model performance and retrieval accuracy.

TavLab, IIIT-Delhi

Plug-and-Play Platform for COVID-19 Resource Allocation

• Developed a reinforcement learning (RL) based platform for efficient resource allocation during the COVID-19 pandemic.
• Designed a generalized platform that could optimize the allocation of any resource by taking input datasets and considering relevant columns.
• Applied actor-critic methods to optimize allocation, ensuring a scalable, plug-and-play system for varied use cases.

Wireless Systems Lab, IIIT-Delhi

Vehicular Planning using Deep Reinforcement Learning

• Developed a multi-modal deep RL architecture using actor-critic methods, ingesting both local and extended roadside views to optimize vehicular decision-making.
• Designed dual-output policy network to jointly select planner actions (acceleration, lane change) and query targets in extended view, reducing bandwidth usage and action space by 90%.

B.Tech. Thesis

Federated Learning with unannotated data

• Developed a novel FL algorithm for unsupervised and personalized representation learning, later published in ICASSP 2024.
• Used Variational AutoEncoders to formulate clients' unlabelled and non-IID data to gaussian distributions.
• Aggregated distributions using mean-field formulation. Used importance sampling based weights for calculating reconstruction loss.
• Is-FedVAE outperformed SoTA FL baselines and demonstrated faster convergence and higher accuracy.

OPAL, Carnegie Mellon University, Advised by Dr. Gauri Joshi

LLM Fill-in-the-Blank Correction

• Exploring adaptive LLM text infilling to correct errors without full regeneration, leveraging bidirectional context for more robust reasoning.
• Research focus on improving inference efficiency and structured generation.

Master of Science

Carnegie Mellon University, School of Computer Science

Intelligent Information Systems

• Ongoing research at OPAL, advised by Dr Gauri Joshi, in efficient inference methods.
• Deep Learning Systems
• Machine Learning
• Advanced Natural Language Processing

Bachelor of Technology

Indraprastha Institute of Information and Technology Delhi (IIITD)

Computer Science and Applied Mathematics

• Algorithm Design and Analysis
• Deep Learning
• Reinforcement Learning
• Artificial Intelligence
• Data Mining
• Teaching Assistant - Computer Organization
• Teaching Assistant - Introduction to Programming