d-Matrix, founded in 2019, builds computing platforms specifically for generative AI inference. The Santa Clara-based company addresses a fundamental challenge in AI deployment: the data movement bottleneck between memory and processors. Its approach centres on digital in-memory compute technology, which processes data where it is stored rather than shuttling it back and forth, reducing latency and energy consumption.
The company's main product, Corsair, is a computing platform designed for running generative AI at scale. It aims to deliver ultra-low latency and high throughput while keeping energy costs manageable - a growing concern as AI workloads expand across industries. The platform targets the AI infrastructure and generative AI inference verticals.
d-Matrix employs over 200 people, with expertise spanning digital in-memory compute, silicon design, software engineering, and systems engineering. The company describes its culture as rooted in first-principles thinking, tackling problems at the intersection of hardware and software. Its stated mission centres on making AI sustainable and commercially viable at scale.
