I am pursuing an MSc in Computing (Artificial Intelligence and Machine Learning) at Imperial College London, after completing a B.Tech in Computer Science and Engineering at IIT Jodhpur. My work focuses on multimodal AI, including vision-language models, audio-visual speech recognition, and speech tokenization. I have published at EMNLP and WACV, and I have experience with RL-based post-training, reproducible PyTorch pipelines, and applied model deployment. Before graduate study, I worked as a Research Engineer at MetaFusion, where I built and deployed vision-language systems for traffic analytics and automated monitoring.