I’m a passionate Software Engineer and full-stack developer currently pursuing my Master’s in Computer Science at George Washington University. With hands-on experience across the U.S. and India, I’ve built and deployed scalable web applications using React, Node.js, Next.js, and cloud platforms. On the machine learning side, my work spans applied AI systems such as ML-based video surveillance anomaly detection, as well as NLP models that analyze large-scale documents for risk, compliance, and decision support using transformer-based architectures like BERT/Legal-BERT, topic modeling, and sentiment analysis. I’ve also built real-time full-stack products for companies like AGLINT and Data Science for Sustainable Development, integrating these ML capabilities into production-ready systems. I’m especially driven by the intersection of AI and practical problem-solving. Beyond tech, I’m a curious learner always exploring new tools, frameworks, and ideas to push boundaries and build impactful solutions.
A quick snapshot of my academic journey, coursework, and highlights.
Washington, DC, USA
Master of Science in Computer Science
GPA: 3.57/4.0
Bangalore, India
Bachelor of Engineering in Computer Science
GPA: 3.4/4.0
From internships to full-stack roles , here’s what I’ve been building
Full Stack Developer
Washington, DC, USA
Full Stack Developer
San Francisco, California
Full Stack Intern
Bangalore, India
Operations Intern
Bangalore, India
Built an intelligent governance-document analyzer for the Inter-American Development Bank using BERT/Legal-BERT. Achieved 81% precision and 78% recall on risk classification while reducing review time by 40%.
Developed a machine learning system to predict CKD risk using clinical lab parameters. Cleaned data, handled missing values, and optimized models including Random Forest, SVM, and XGBoost to achieve 98% accuracy.
Developed a Swift-based iOS app enabling dog owners to match playmates through swipe-style interactions. Built using SwiftUI, MVVM architecture, and reusable UI components.
Built a deep-learning system to detect abnormal activities in surveillance footage using CNN + LSTM architectures. Achieved high accuracy in identifying unusual behaviors, reducing false positives and enabling real-time security monitoring.
Designed and implemented a relational database and UI system enabling efficient cataloging, search, and management of artwork collections and exhibition data.
Machine learning system built to predict early-stage disease risk using clinical and demographic data. Applied feature engineering, model tuning, and evaluation across multiple classifiers.