Graduate Machine Learning Researcher and Backend Engineer with expertise in predictive modeling, statistical analysis, and computer vision. Co-authored a peer-reviewed paper on algorithmic bias in AI systems. Skilled in building ML pipelines, feature engineering, model evaluation, and deploying scalable data systems.
Location: Flint, MI
Email: ritikg@umich.edu
M.S. Computer Science & Information Systems (ML/Data Science)
B.S. Computer Science & Information Technology
Graduate Research Assistant (Summer Research)
Backend Developer (Data Systems)
Junior Backend Developer
Scikit-learn, Pandas, NumPy, Feature Engineering, Cross-Validation, Ensemble Models, ROC-AUC, Hypothesis Testing, ANOVA, Matplotlib, Seaborn
PostgreSQL, MySQL, SQLite
Python, SQL
OpenCV, YOLOv8, Object Detection, Video Analytics, AWS, Docker, Git, Linux, Apache Airflow
FastAPI, Django, Django Rest Framework, LangGraph
2
2
30
1
Predictive modeling, ensemble classifiers, feature engineering, and model evaluation
ANOVA, correlation analysis, hypothesis testing, and data-driven insights
Object detection, player tracking, video analytics with OpenCV and YOLOv8
FastAPI, Django REST Framework, PostgreSQL, and scalable microservices
ETL pipelines, Apache Airflow, data processing at scale
AWS, Docker containerization, and deployment automation
Peer-reviewed research on algorithmic bias in cloud-based AI decision systems, published in Applied Sciences (MDPI).
How ensemble classifiers and computer vision are revolutionizing soccer analytics through player tracking and match prediction.
Building autonomous multi-agent research systems with LangGraph, featuring human-in-the-loop validation and prompt optimization.