I am a Data Science graduate student at the University of Maryland College Park with a strong foundation in Machine Learning, AI, and NLP. With experience in developing and implementing machine learning models, automating testing processes, and creating innovative solutions, I am passionate about leveraging data to solve complex problems and drive impactful decisions.
My technical expertise spans across Python, Machine Learning frameworks, MLOps tools, and cloud technologies. I have successfully applied these skills in professional settings and academic projects to deliver efficient and effective solutions.
I'm particularly interested in leveraging AI solutions to solve real-world challenges in healthcare, sustainability, and business optimization. My approach combines theoretical knowledge with practical implementation, ensuring that my solutions are both innovative and deployable in production environments.
Get In TouchBuilt an end-to-end Retrieval-Augmented Generation system with agent-based coordination, reasoning, and validation. Integrated Streamlit UI with LangGraph for real-time multi-agent execution and dynamic query routing. Used RAG-Fusion retrieval for office docs, web pages, and knowledge graph extraction with Graph-of-Thought reasoning for explainable outputs.
Developed a machine learning-based system to identify and categorize hate speech in online text using NLP techniques. Implemented and compared Naive Bayes, LSTM, and DistilBERT models, with DistilBERT achieving 94% accuracy. Delivered data-driven recommendations to improve content moderation policies.
Created a deep learning system for monitoring tomato plant health, utilizing YOLOv8 to achieve 92% accuracy in classifying Early Blight, Healthy, and Magnesium Deficiency conditions. Designed an innovative rail system for real-time video capture with a user-friendly web interface.
Developed a model for credit score classification into High, Medium, and Low categories using K-NN, PCA, SVM, and Neural Networks. Applied PCA for dimensionality reduction and optimized classification accuracy through multiple algorithms, leading to an 87% improvement in prediction performance.
Created an open-source Python software integrated with MySQL for efficient file organization and retrieval. Designed a user-friendly tag-based system enabling users to categorize and locate files based on content or purpose, enhancing productivity in complex data environments.
Innovated a machine learning model for crop prediction based on soil parameters like nutrients and moisture levels. Employed Python and LightGBM for model creation, and Flask for integrating the model with a user-interactive website. Delivered a platform enabling users to receive tailored crop recommendations, enhancing agricultural decision-making.
Coursework: Statistical methods in Data Science, Automated Learning and Data Analysis, Big Data Systems, Design and Analysis of Algorithms.
GPA: 8.16/10
Coursework: Machine Learning, Artificial Intelligence, Natural Language Processing, Applied Analytics, Cloud Computing, Computer Networks, Databases, Operating Systems, Computer Architecture, Digital Image Processing.
Completed advanced training in deploying AI models on edge devices using Intel's frameworks and tools.
Gained comprehensive knowledge of machine learning concepts and their implementation on AWS.
Mastered foundational AWS cloud concepts, services, and implementation strategies.
Advanced understanding of AWS cloud architecture, security, and optimization techniques.
Comprehensive training in Python programming fundamentals, advanced concepts, and practical applications.