At Brain Station 23, I test the Library Management System (LMS) and Laboratory Information Management System (LIMS), covering functional, regression, sanity, and end-to-end scenarios. I also investigate client-reported LMS issues and validate fixes.
For LIMS, I develop and maintain Playwright automation tests in TypeScript, extending the existing codebase with additional regression scenarios. I test web and desktop applications, including production-build validation.
As a Research Intern at Applied Intelligence and Informatics Lab (AIIL), I contributed to baseline YOLOv12 and hybrid H-YOLOv12-KAN model development by integrating KAN-based modules. I prepared a fabric defect dataset and developed PyTorch training pipelines, while assisting with model training and evaluation.
My projects include a manual, automation, and API testing project for Evershop, and a Playwright framework for SauceDemo using Page Object Model and data-driven testing. I also co-authored a paper evaluating machine learning models for predicting Olympic medal outcomes.
