CS & Data Science Student
I build software and data systems at the intersection of engineering, computation, and research.
CS & Data Science student working on large-scale data pipelines, cloud systems, and computational modeling.
Professional Experience
Software Development Intern
National Bioforensic Analysis Center (NBFAC)
- →Building a project that uses large-scale sequence searches over public sequencing data.
- →Analyzing global distribution patterns of microbial pathogens and closely related organisms.
Research Assistant
Mount St. Mary's University
- →Researched atomic interactions and molecular orbital behavior using neural network potentials.
- →Analyzed molecular simulations using matrix-based methods to evaluate energy and force behavior.
- →Compared neural network architectures and presented findings in a research poster.
Skills: Neural Networks, PyTorch
Undergraduate Research Assistant
Mount St. Mary's University
- →Set up and managed multi-node Kubernetes clusters using kubeadm.
- →Deployed Dockerized services and managed pods and services.
- →Troubleshot cluster configuration, networking, and node-level issues.
Skills: Kubernetes, Hadoop, containerized systems
Software Engineering Intern
Headstarter
- →Built an AI-powered flashcard web application using React, JavaScript, and Firebase.
- →Integrated OpenAI API for content generation and Stripe for payments.
- →Improved frontend performance and overall user experience.
Skills: React.js, Next.js, OpenAI API, Stripe
Research and Software Tools
My Projects
NBA Referee Bias Tracker
Data-driven analysis platform investigating referee bias patterns across NBA seasons. Built with Python data pipelines, statistical analysis, and interactive dashboards to quantify officiating inconsistencies.
Talib-Al Ilm Library
Full-stack digital library platform designed to manage large collections with advanced search and filtering. Built with Next.js and a PostgreSQL-backed backend, focusing on database design, API structure, authentication, and a responsive user experience for real-world content management.
Play2Win
High-performance sports analytics platform with real-time data processing and predictive modeling. Combines data engineering pipelines with frontend performance optimization.
Flashcard SaaS
AI-powered learning platform implementing spaced repetition and adaptive algorithms. Full-stack solution covering payment integration, user analytics, and scalable backend architecture.
Premier League Prediction Model
Machine learning system predicting match outcomes using ensemble methods on historical data. Implements feature engineering, model validation, and probabilistic forecasting.
Get in Touch
I'm always interested in exploring new opportunities and connecting with fellow engineers and researchers. Feel free to reach out.
Or shoot me an email at taha.sh4h@gmail.com