I'm a tech enthusiast with a strong desire to learn and grow. I've self-taught various programming languages and technologies, and I'm always on the lookout for opportunities to advance my abilities. I'm an enthusiastic, people-oriented individual who enjoys expanding my network and collaborating with like-minded professionals. I thrive on the excitement of learning and look forward to contributing my passion for technology to any team or project.
Research, machine learning, and production systems.
Student Researcher
UC San Diego Shiley Eye Institute
Working on developing multimodal deep learning models to enhance glaucoma diagnosis and progression prediction by integrating longitudinal and cross-sectional ocular data—including imaging, clinical, and temporal signals. Designing architectures that leverage temporal analysis to identify patients at risk of rapid progression or requiring surgical intervention, improving early detection accuracy and supporting clinical decision-making. This research tests the hypothesis that multimodal longitudinal models outperform traditional cross-sectional approaches in predicting glaucoma outcomes.
ML Intern
Sudha Gopalakrishnan Brain Centre - IIT Madras
Trained and fine-tuned YOLOv9 on a curated brain segmentation dataset (25 target sections), achieving a Dice score of 0.97 and 30% inference speed improvement through a novel post-inference processing technique to address YOLO limitations. Worked on developing an innovative neural network model extending YOLOv9, enabling end-to-end brain region segmentation without post-inference steps. Designed and implemented robust data preprocessing and annotation pipelines, ensuring high-quality inputs for model training and evaluation.
Engineered a structured-data pipeline transforming Hindi WordNet into 1.25M instruction-response pairs, forming the basis of a research manuscript submitted to ACL 2026. I fine-tuned Gemma-3-12B using QLoRA with 4-bit quantization, achieving a 91.0 pedagogical effectiveness score—surpassing GPT-4.1. The system demonstrated an 86% improvement in consistency, validating the approach for low-resource languages. Additionally, I built and deployed a context-aware keyword detection microservice with FastAPI, improving contextual understanding accuracy by 25%.
As part of Project AISHA 2.0, I contributed to multiple stages of developing an in-house, Retrieval-Augmented Generation (RAG)-based chatbot built from scratch. My key responsibilities included research on indexing and retrieval process which included comparison of various vector data stores to optimize the application. Additionally, I developed an enhancement service that significantly improved the chatbot's performance, reducing resource usage while accelerating response times. I also worked on Large Action Model development.
Specialized in leveraging Google Suite and Google Apps Script to create and manage various applications and manipulate data across the company's database. Developed and deployed a comprehensive warehouse management application featuring a QR generator and scanner. This system included a detailed database providing all necessary information for the warehouse manager, automating process and significantly increasing accuracy, speed, and cost-efficiency in the management process.
Applied builds across LLMs, security, automation, and full-stack systems.
Automated Incident Response: Leveraging LLMs for Rapid Post-Attack Analysis and Reporting
Developed an AI-driven automated incident response framework integrating on-device Large Language Models (LLMs) and specialized classifiers to streamline post-attack analysis, reducing response times from days to hours. Architected a system for real-time log ingestion, multi-source data correlation, and comprehensive report generation, enabling rapid, accurate threat detection and response across networked environments.
Cybersecurity • Incident Response • Automation • Large Language Models (LLMs) • Machine Learning • Python • Flask • Wazuh • Suricata • SMTP • Log Analysis • Hugging Face • API Integration • Machine Learning • Log Analysis
Contributed to the design and leading development of AI-powered features—including course summaries, peer-driven insights, and coding assistance—by leveraging advanced language models such as LLaMa3-70B. Integrated the vLLM inference engine to improve the efficiency and performance of LLM queries, reducing latency and enabling scalable AI-generated responses across the system. Developed and deployed multiple AI-driven endpoints using FastAPI, with version control through Git and agile management under Scrum methodology. Ensured robustness and reliability of application components by writing unit tests and performing debugging with pytest, ultimately enhancing the overall learning experience for students.
Large Language Models • FastAPI • vLLM • Python • OpenAI
Developed machine learning models to accurately predict food ratings based on recipe information and user reviews. Preprocessed and engineered features from a dataset containing multiple attributes. Evaluated multiple algorithms including logistic regression, boosting techniques like AdaBoost, and advanced algorithms like Multi Layer Perceptron. Achieved an accuracy of 77.166% by implementing a logistic regression model.
Developed ShelfSense, a full-stack Library Management System with a Flask (Python) backend and Vue.js frontend, supporting comprehensive operations such as book management, user authentication, issue tracking, and user feedback. Designed a secure system with role-based access control and a RESTful API architecture. Implemented automated testing using Selenium to ensure reliability. Built a scalable backend leveraging SQLAlchemy ORM for database operations, Redis caching for performance optimization, and Celery with RabbitMQ for background task scheduling, enabling automated reminders and report generation.
Built a robust music streaming app using Flask, SQLite, SQLAlchemy, and HTML/CSS/JavaScript. It mimics mainstream platforms with features like user registration, artist following, playlist creation, song rating/commenting, and extensive search capabilities. Users can create and manage their songs/albums, and an admin panel allows CRUD operations and provides detailed statistics. I also integrated Flask-Restful for API endpoints, enabling seamless interaction and CRUD operations.
Involved in the development of Phishit, a browser extension aimed at bolstering online security. The project utilizes HTML, CSS, JavaScript, Python, and machine learning (scikit-learn) to scan open email content, transmit it to a server, and detect potential phishing attacks. My role included development of machine learning models, web development and server scripting. Phishit represents a significant step towards proactive phishing threat identification.
Developed 'Judge My Music,' a web app using Spotify API, HTML, CSS, JavaScript, and Vite framework. Integrated browser local storage for enhanced user experience and Selenium web scraping for artist data enrichment. The platform provides amusing music insights and recommendations, showcasing my blend of technical skills and creativity to entertain while celebrating diverse music tastes.
HTML5 • CSS3 • JavaScript • Vite • Selenium • Spotify API
Led the data analysis for Project Shilpkaar, a venture aiding underprivileged weavers and addressing plastic waste. Responsibilities include data collection, cleaning, customer segmentation, product costing, and supply chain insights. Continuous analysis aimed to uncover sales trends, customer preferences, and optimization opportunities. Dedicated to enhancing Shilpkaar's operations through actionable insights and innovation.