CS Graduate Student at Texas Tech University. I build full-stack applications, craft ML-powered solutions, and love turning complex problems into clean, working software.
M.S. Computer Science
I'm a Computer Science graduate student at Texas Tech University, passionate about crafting solutions that sit at the intersection of full-stack development and machine learning. With a background in both software engineering and cybersecurity, I bring a security-first mindset to every project I build.
My journey started with a B.S. in Computer Engineering from Kathmandu, Nepal, where I developed a deep foundation in systems thinking. Since then, I've contributed to Agile development teams, identified security vulnerabilities, and built predictive analytics tools used for real-world decision-making. I thrive in collaborative environments and love tackling challenges that require both analytical thinking and creative problem-solving.
Core interests
"I believe that clean code, thoughtful architecture, and a user-first perspective are the hallmarks of truly great software."
Technologies and tools I've worked with across development, data, and security.
A selection of projects spanning payroll systems, predictive analytics, and ML-based security tools.
A full-stack enterprise payroll platform built with Oracle Database and Oracle APEX. Automated payroll calculations and leave processing through stored procedures, triggers, and cursors. Features role-based authentication with audit logging for compliance, and is containerized with Docker for cross-platform deployment.
A predictive analytics system that forecasts insurance complaint settlement outcomes in Texas. Applied data preprocessing, feature engineering, and supervised learning algorithms achieving 15% accuracy improvement. Integrated the trained model into a Django-based RESTful web application for real-time inference.
A Django-based health risk prediction tool that provides personalized feedback using clustering and classification models. Tackled challenging requirements by combining multiple ML approaches — ensemble methods improved model reliability and interpretability for end users.
An ML-based system for identifying anomalous activities in user behavior data. Implemented Random Forest and SVM classifiers with rigorous feature selection, normalization, and hyperparameter optimization to achieve high precision in detecting unusual patterns.
Graduate program with a focus on algorithms, machine learning, and software systems. Actively applying coursework to real-world problems through hands-on projects in predictive analytics and full-stack development.
Comprehensive foundation in computer science fundamentals, hardware systems, software engineering, and embedded systems. Developed strong problem-solving skills and a systems-level understanding of computing.
Whether it's a job opportunity, collaboration, or just a quick hello — my inbox is always open.
I'm currently open to internships and full-time opportunities in software engineering, machine learning, or security. Feel free to reach out via any of the channels below.