NVIDIA has invested over $900 million to acquire the Enfabrica team and technology, enhancing its AI supercomputing layout.

The chip giant NVIDIA ( has recently invested over 900 million USD to recruit AI hardware startup Enfabrica's CEO Rochan Sankar and its employees, while also acquiring the company's technology licensing. Enfabrica is known for its technology that allows over 100,000 GPUs to connect efficiently, which is expected to strengthen NVIDIA's layout in AI large-scale computing clusters.

What is the founding background of Enfabrica, and what are its strengths?

Enfabrica was founded in 2019 by Rochan Sankar, a former senior executive at the well-known technology company Broadcom ), and Shrijeet Mukherjee, who has worked in technology development at Alphabet.

Two individuals formed a team with 120 core engineers from previous companies such as Intel, Cisco, and Meta, focusing on solving issues related to the expansion of AI infrastructure, such as improving data transmission and network computing bottlenecks.

The core technology of Enfabrica lies in the creation of a dedicated network chip that can rapidly connect 100,000 AI computing chips, allowing the large chip cluster to operate in coordination, much like a supercomputer. This design can significantly reduce data transmission delays and chip idling issues caused by insufficient network bandwidth, while also providing higher computational efficiency.

The image shows Enfabrica's innovative technology diagram for chaining GPUs.

More importantly, Enfabrica allows AI chips to connect directly to lower-cost DDR5 memory, replacing the expensive high-bandwidth memory (HBM), effectively reducing data center memory costs while maintaining system performance. As of 2025, it has raised approximately $260 million.

The explosive demand for technology drives a major update of NVIDIA's AI products.

With the surge of generative AI, NVIDIA's products have evolved from a single GPU card to high-density computing systems in rack form. The early A100 chips were mainly installed in servers as single processors, while the latest generation has been upgraded to tower racks that can accommodate 72 GPUs per rack.

This architecture is precisely the core configuration for Microsoft (Microsoft)'s recent investment of $4 billion to build data centers in Wisconsin. Enfabrica's ultra-large-scale interconnect technology perfectly complements NVIDIA's critical piece in the layout of giant systems, providing strong support for its continued leadership in global AI computing.

9 million dollars to recruit the Enfabrica team, further expanding the global AI layout.

According to a recent report by CNBC, Nvidia spent over $900 million in cash and stock to recruit Enfabrica's CEO Rochan Sankar and core members, while also acquiring the company's technology licensing. The transaction was completed last week.

This is another significant move in the AI landscape following the acquisition of the Israeli software optimization company Run:ai for 700 million USD in 2024, an investment of nearly 700 million USD in the UK data center startup Nscale, and the announcement this week of a 5 billion USD partnership with Intel to collaborate on AI processors.

Through the dual enhancement of technology and talent, NVIDIA continues to consolidate and expand its leading advantage in the global AI supercomputing field.

( Chip Alliance Major Restructure! Nvidia invests 5 billion dollars in Intel to jointly develop AI and PC chips )

This article reports that Nvidia has invested over 900 million USD to recruit the Enfabrica team and technology, strengthening its AI large-scale computing layout. It first appeared in Chain News ABMedia.