Built by experts
in wearable AI.

Santosh is a state endowed Chair of Excellence Professor in Computer Science and director of two NIH funded national research centers on wearable AI.

Over eighteen years he has built research teams spanning more than twenty universities, including Harvard, Carnegie Mellon, Cornell and UCSF, on federally funded work worth more than $50 million. Those studies collected sensor data across roughly 106,000 days of ordinary life: people at work, in traffic, in difficult conversations, rather than sitting in a lab. His teams used it to build AI that detects stress and stressful conversations from the wrist, and to learn when an intervention actually lands. His group's PPG foundation model, Pulse-PPG, is open source and now used as a reference point by other research groups.

He has spent equal effort on the other side of the problem: what wearable data can reveal about a person, and how to keep it from being misused. That research is why CuesHub is built the way it is.

Popular Science named him one of its Brilliant Ten in 2010, and he has been invited to the White House to speak on the future of biosensors. For fifteen years he has taught physicians, psychologists and nurses to use this technology in their own research, which is to say he has spent a long time explaining it to people who are not engineers.

Tim spent nine years as Chief Software Architect and then Deputy Director of MD2K and mDOT, the NIH-funded national centers on wearable AI. He was recognized with the University of Memphis' Presidential Excellence Award in 2017.

He converted state-of-the-art research and science info phone and watch apps, and the cloud behind them. His work was deployed at more than a dozen medical schools to study: stress, work performance, chronic pain, smoking cessation, heart failure and oral health. His plaform collected, stored, and analyzed hundreds of terabytes of participants' data under federal research rules.

Through these experiences, he gained expertise in extracting actionable intelligence from large volumes of noisy physiological data collected by wearables, and embedding complex AI into battery-powered, low-resource smartwatches.