About Me

Research and Teaching Assistant at UB

As a Research Assistant, I focus on optimizing energy consumption in deep learning models to promote sustainable computing. Using Python, C++, and in-depth knowledge of operating systems and Linux environments, I implement and analyze complex computational frameworks. My work involves calculating the exact memory usage and execution time required to run deep learning programs on a single CPU core. By leveraging advanced techniques such as multiprocessing and parallel computing, I develop precise methods for energy and performance profiling. This research enhances understanding of how computational efficiency can be improved in resource-intensive applications, contributing to greener computing practices.

In addition to research, I serve as a Grader for a graduate-level Machine Learning course, where I assess assignments, review projects, and provide constructive feedback to students. I assist in clarifying challenging concepts, guiding students on algorithms, and ensuring they grasp key principles of machine learning. This dual role enables me to apply my technical expertise while fostering an environment of learning and collaboration.

Work Highlights at Experian

Throughout my career, I have had the opportunity to lead and develop complex software solutions, with a strong focus on both front-end and back-end technologies. One of my most significant contributions was leading the development of the CPD Waterfall tool for the Experian Verification Solution. In this role, I was responsible for creating an intuitive user interface using JSP, ExtJS, and JavaScript, enabling users to easily upload PII data and download credit reports. On the back-end, I utilized Java Spring and Hibernate to design and develop key components, including Controllers, Services, and DAOs, ensuring robust services and smooth database interactions. Additionally, I automated key processes with Quartz Scheduler and Cron Jobs, streamlining the process of fetching reports from external APIs. I also played a pivotal role in addressing technical debt by fixing numerous bugs, contributing to the migration from Spring 4 to Spring 5, and resolving various security vulnerabilities, ensuring the application remained up-to-date, secure, and resilient.

Alongside these projects, I enhanced the CS-Access-Automation tool, which involved integrating Python Robot Framework and Selenium WebDriver to improve testing accuracy and reliability. I contributed to expanding the tool’s test coverage and refining error reporting to ensure actionable results. These enhancements improved the overall efficiency and stability of automated testing, supporting faster development cycles and more reliable product delivery.

Experian Internship Overview

Throughout my career, I have had the opportunity to lead and develop complex software solutions, with a strong focus on both front-end and back-end technologies. One of my most significant contributions was leading the development of the CPD Waterfall tool for the Experian Verification Solution. In this role, I was responsible for creating an intuitive user interface using JSP, ExtJS, and JavaScript, enabling users to easily upload PII data and download credit reports. On the back-end, I utilized Java Spring and Hibernate to design and develop key components, including Controllers, Services, and DAOs, ensuring robust services and smooth database interactions. Additionally, I automated key processes with Quartz Scheduler and Cron Jobs, streamlining the process of fetching reports from external APIs. I also played a pivotal role in addressing technical debt by fixing numerous bugs, contributing to the migration from Spring 4 to Spring 5, and resolving various security vulnerabilities, ensuring the application remained up-to-date, secure, and resilient.

During the Experian Hackathon, I developed a Java Spring Boot and Hibernate web application, called the Transactions Application, to streamline internal employee workflows. The application allows easy access to various subcode information and specific transaction details made by end users. My contributions significantly enhanced the productivity of the production team by providing them with a tool that accelerated the ticket resolution process. The application saves approximately 10 minutes per new ticket, which directly improved response times and overall efficiency for the team. This experience allowed me to leverage my skills in full-stack development and contribute to a solution that had a tangible impact on operational productivity.

Research Assistant at KMIT

During my research internship at the Research and Development Lab of Keshav Memorial Institute of Technology, I actively contributed to advancing medical imaging analysis, focusing on breast carcinoma pathology. I developed and refined AI-based deep learning models to detect tubules in whole-slide images, enhancing the accuracy of medical diagnostics. Leveraging frameworks like Faster R-CNN and YOLOv5, I designed a robust pipeline to identify mitosis in digitized pathology images, significantly aiding in breast cancer detection. I demonstrated expertise in utilizing tools such as QuPath to construct systematic workflows for annotating Whole Slide Imaging (WSI) TIFF files, producing high-quality images and masks for accurate labeling. Collaborating within a four-member team, I effectively handled image preprocessing, implemented distributed training strategies, and showcased strong leadership and presentation skills. These efforts highlighted my ability to tackle complex challenges in the intersection of AI and medical research.