I am a researcher passionate about pushing the boundaries of Deep Learning, specifically in the realms of video understanding, spatiotemporal learning, and efficient model design. Currently working as a Research Engineer at KAUST (King Abdullah University of Science and Technology), my work focuses on action recognition and representation learning from video data.

Beyond research, I am a dedicated open-source developer, committed to bridging the gap between cutting-edge academic research and real-world software applications. I believe in building tools that make complex AI technologies accessible and efficient.