Applied ML Scientist and Engineer specializing in Generative AI, Computer Vision, and Multimodal Systems. Focuses on building, evaluating, and deploying models for diffusion systems, vision-language alignment, and human-centered visual understanding.
- Generative Modeling: Diffusion architectures, text-to-image synthesis, stylized font generation, drag-based editing.
- Multimodal Systems: Image-text-to-text Applications, Vision-language alignment, 3D asset validation and Judging
- Evaluation & Data: Designing reproducible ML pipelines, quality assessment metrics, actionable dataset curation.
Prioritizes data-centric ML workflows over model scaling. Transforms research prototypes into reliable evaluation pipelines and production-ready systems. Bridges the gap between academic exploration and industrial application in generative modeling.
- Role: Senior ML Scientist / Engineer, Generative AI
- Education: PhD in Computer Vision and Machine Learning