I am a researcher working in AI-driven software testing, with a particular interest in Large Language Models and automated web-application testing. My recent work includes AutoQALLMs, a framework that uses LLMs to generate and execute Selenium test scripts, which has been accepted for publication. My current research focuses on building intelligent testing systems that combine LLMs and multimodal models for self-healing tests, adaptive reasoning, and visual validation. I am especially interested in grounding these models through fine-tuning, curated datasets, and practical evaluation on real-world applications. I aim to develop reliable, autonomous testing workflows that reduce maintenance effort and support explainable decision-making in modern web-based systems.