I am a Senior Applied Scientist in the AGI team at Amazon, where I work on advancing research in image generation/editing diffusion models and multimodal large language models. I am a core contributor of Amazon's flagship foundational models: Nova 2, Nova 1, and Titan Image Generator models.
Previously, I worked as a researcher at Fyusion, where I worked on problems related to 6DOF pose estimation, object detection and segmentation, and distillation of large models.
Even before that, I completed my masters in computer vision (MSCV) at Carnegie Mellon University advised by Professor Katerina Fragkiadaki.