I am a computer vision researcher with an emphasis on multimodal AI. My previous work has focused on sample-efficient markerless tracking in video data, as well as low-latency model deployment. I am currently working with multimodal/Vision-Language models with their applications in AI-smart devices and robots. What makes me unique is that I am also a strong communicator. When formulating a problem, I know how to question the user/client to understand specifications. This, paired with my technical ability, enables me to create effective solutions.