Yash Gugale

Bio:

Yash Gugale is a Senior Forward Deployed Engineer at TwelveLabs in New York City. He works with robotics labs, data-collection platforms and enterprise teams to put TwelveLabs' video foundation models into production: Marengo for multimodal embeddings and search, and Pegasus for video-language understanding and segmentation.

His current focus is physical AI, and in particular the data-readiness gap between capturing egocentric video (head or body cam) and training robot policies on it. He designs curation pipelines that grade raw footage for usability, flag faces and other personal information, cut idle time, and surface rare or duplicate clips; and dense-captioning pipelines that segment footage into atomic hand-object interactions and fill a schema the data owner controls (action, object, tool, acting hand, quality). He builds the golden-set evaluation harnesses used to check those labels.

Before that, Yash spent about six years in video streaming engineering at Peloton and Samsung TV Plus, and his TwelveLabs work also includes semantic search over media archives, metadata enrichment and live HLS video analysis. He holds an MS from Purdue University and an MBA from the Gies College of Business at the University of Illinois Urbana-Champaign.