Superconducting chip startup, Snowcap Compute, has launched with a $23 million seed funding round.

In addition to the funding round, which was led by Playground Global, Snowcap also announced that former Intel CEO, Pat Gelsinger, has joined its board.

The seed round also saw participation from Cambium Capital and Vsquared Ventures.

The startup is planning to develop AI chips based on superconducting technology and says its architecture has been engineered for “extreme performance and energy efficiency,” enabling a “new class of data centers optimized for AI, quantum, and high-performance computing (HPC).”

According to a report from Reuters, Snowcap claims its chips will have a 25x performance per watt improvement over the current best available chips, even after energy used for cooling has been accounted for.

The chips will be made using niobium titanium nitride, a material well known for its superconducting properties. Snowcap intends to have its first basic chip available by the end of 2026, but the timeline for full system availability has not been disclosed.

Led by CEO Michael Lafferty, who previously spent ten years at Cadence, including three years as director of its “More than Moore” engineering group, Snowcap’s executive team also includes CTO, Quentin Herr, PhD, and chief science officer, Anna Herr, PhD, who have held roles at Northrop Grumman and Imec.

Brian Keller, former SVP of GPU engineering at Nvidia, and Phil Carmack, former VP of silicon engineering at Google, have been named as advisors to Snowcap.

“We’re building compute systems for the edge of what’s physically possible,” said Lafferty. “Superconducting logic lets us push beyond the limits of existing CMOS technology, achieving orders-of-magnitude gains in processing speed and efficiency. That performance is essential for the future of AI and quantum computing.”