.png&w=256&q=75)
6
3
United States
1 year of experience
As an AI student specializing in Data Analytics, I am passionate about leveraging data-driven insights to solve complex problems and drive innovation. My academic journey has provided me with a solid foundation in mathematics, programming, and analytical thinking, which I now apply to emerging fields such as machine learning, big data analytics, and large language models (LLMs). My research focuses on reinforcement learning (RL) for single and multi-agent systems, where I design algorithms to optimize target-capturing tasks in dynamic environments like grid-based simulations and robotic navigation. I am deeply interested in exploring how advanced analytics and AI can transform industries by uncovering patterns, optimizing processes, and enabling smarter decision-making. This includes training RL agents using Q-learning, Deep Q-Networks (DQN), and policy gradient methods to adapt to competitive/collaborative scenarios. Whether it’s designing scalable data pipelines, developing predictive models, experimenting with LLMs, or analyzing emergent behaviors in multi-agent systems, I thrive at the intersection of theory and real-world application.
QubicGuard is an AI-driven transaction monitoring system built for the Qubic blockchain ecosystem. It collects live transaction data using a Flask-based webhook and simulates realistic transactions for testing purposes. The data is stored in a JSON file and displayed on an interactive Streamlit dashboard, which updates in real-time. High-risk transactions are automatically detected based on a computed risk score, providing immediate alerts to users. The dashboard visualizes transaction trends, amounts, and types, enabling actionable insights and proactive risk management. QubicGuard combines blockchain data integration, AI analytics, and user-friendly visualization, demonstrating innovation, practical utility, and readiness for real-world deployment in hackathons.
7 Dec 2025
Our project, Flood Forecasting Agent, leverages AI and real-time geospatial and weather data to predict flood risks and identify nearby safe locations. The system consists of two collaborating agents: the Flood Risk Agent, which forecasts flood probability for a given location, and the Safety Agent, which recommends safer nearby areas. Built with a Streamlit front-end, the app visualizes forecasts in tables, charts, and interactive maps. We have also exposed API endpoints for potential integration. This solution demonstrates practical agentic software using Coral protocols and addresses real-world flood preparedness challenges effectively.
21 Sep 2025
Our project is a python based application designed to assist patients in analyzing their prescriptions. By uploading their prescriptions and entering medicine names, the app uses transformers(huggingface) to assess the need for a second opinion. It also provides personalized suggestions for questions patients (before taking prescribed medicines) to ask their doctors to avoid potential side effects or medication-related issues. The app aims to empower patients to make more informed decisions about their health, promoting safer medication practices and fostering communication between patients and healthcare professionals.
1 May 2025
.png&w=640&q=75)
.png&w=640&q=75)
.png&w=640&q=75)
