About

Tandemn is a team of researchers, ML and systems engineers, and mathematicians from UIUC and UCLA. We have worked across the AI stack since before large language models entered the mainstream, from early NLP research to modern inference infrastructure. Along the way, we saw firsthand how difficult it is to secure compute, deploy models efficiently, and make full use of available hardware. We built Tandemn to remove that complexity and make inference infrastructure simpler, more flexible, and more efficient. We are also strong believers in open-source infrastructure, and build Tandemn openly for anyone to use, inspect, and contribute to.