Teja Sree Chiluveru

Conducted applied research on machine learning for environmental monitoring, advancing coastal dune protection, landfill management, and disaster response modeling. Built and validated Python-based ML models with scikit-learn and TensorFlow, achieving 80-95% predictive accuracy and delivering actionable insights for sustainable land-use management and early hazard detection. Designed data pipelines and preprocessing workflows using SQL Server and Python, enhancing data quality and transparency for large-scale geospatial datasets in academic publications. Contributed research outcomes that supported grant proposals and integrated findings into academic publications, bolstering institutional visibility in AI and environmental data science.

Conducted applied ML research on environmental monitoring for coastal dune protection, landfill management, and disaster response modeling. Built and validated Python-based ML models with scikit-learn and TensorFlow achieving 80-95% predictive accuracy. Designed data pipelines and preprocessing workflows using SQL Server and Python to enhance data quality and transparency for large geospatial datasets. Contributed results to grant proposals and publications, strengthening AI and environmental data science initiatives.

Developed and maintained enterprise ASP.NET Core MVC applications using C#, enhancing system scalability and reducing load times by 20% through optimized architecture. Built and integrated 30+ RESTful APIs to support high-traffic, client-facing applications, ensuring 99.9% uptime and accelerating data exchange across business modules. Optimized SQL queries and database logic, reducing query execution time by 25% and boosting the performance of data-intensive applications. Enhanced front-end interactivity by implementing responsive features with HTML5, CSS3, jQuery, Angular, and TypeScript, thereby reducing UI errors and increasing user satisfaction. Architected modular and reusable components following SOLID principles, cutting code duplication by 30% and streamlining future enhancements. Deployed and automated builds using Azure DevOps YAML pipelines and GitLab CI/CD, which accelerated deployment frequency by 35% and ensured consistent delivery. Containerized and orchestrated microser