Neurophos has raised $110 million in an oversubscribed Series A round to accelerate the commercialization of its photonic AI chip technology, positioning the Austin-based company to push beyond the power and scalability limits facing today’s AI infrastructure. The financing brings Neurophos’ total funding to $118 million and was led by Gates Frontier, with participation from M12 (Microsoft’s Venture Fund), Carbon Direct Capital, Aramco Ventures, Bosch Ventures, Tectonic Ventures, Space Capital, and additional investors.
The company is developing what it describes as a new class of AI inference accelerator built on photonics rather than traditional silicon compute architectures. As AI adoption continues to expand across enterprises and consumer services, data centers are contending with rising energy costs, constrained power availability, and increasing difficulty scaling conventional GPU clusters. Neurophos is pitching its approach as a way to keep performance climbing without requiring a proportional jump in electricity, cooling, and physical footprint.
At the center of Neurophos’ platform is a proprietary optical processing unit, or OPU, designed to perform AI inference using light-based computation. The company says its OPU integrates more than one million micron-scale optical processing elements on a single chip and can deliver up to 100 times the performance and energy efficiency of current leading chips. Neurophos also describes its solution as a practical, drop-in replacement for GPUs in data centers, aiming to reduce deployment friction for operators who want faster inference at lower power.
Neurophos attributes its technical breakthrough to micron-scale metamaterial optical modulators, which it says represent a 10,000x miniaturization compared with prior photonic elements. That size reduction, the company argues, makes large-scale photonic computing manufacturable and scalable in a way that earlier photonics efforts could not achieve. By packing dense optical parallelism onto a single chip, Neurophos believes it can improve both throughput and efficiency as systems scale, rather than running into the power walls that increasingly define GPU-based expansion.
The new funding will be used to accelerate delivery of Neurophos’ first integrated photonic compute system, including data-center-ready OPU modules, a full software stack, and early-access developer hardware. Neurophos said it is also expanding its Austin headquarters and opening a San Francisco engineering site to support product development and meet early customer demand.
Neurophos was founded by CEO and co-founder Dr. Patrick Bowen and co-founder Dr. Andrew Traverso. The company says its team includes industry veterans with experience at companies including NVIDIA, Apple, Samsung, Intel, AMD, Meta, ARM, Micron, Mellanox, and Lightmatter. Additional investors in the Series A include DNX Ventures, Geometry, MetaVC Partners, Morgan Creek Capital, Silicon Catalyst Ventures, Mana Ventures, Gaingels, and others. Cooley LLP served as legal counsel on the transaction.
KEY QUOTES:
“Modern AI inference demands monumental amounts of power and compute. We need a breakthrough in compute on par with the leaps we’ve seen in AI models themselves, which is what Neurophos’ technology and high-talent density team is developing.”
Dr. Marc Tremblay, Corporate Vice President and Technical Fellow, Core AI Infrastructure, Microsoft
“Moore’s Law is slowing, but AI can’t afford to wait. Our breakthrough in photonics unlocks an entirely new dimension of scaling, by packing massive optical parallelism on a single chip. This physics-level shift means both efficiency and raw speed improve as we scale up, breaking free from the power walls that constrain traditional GPUs.”
Dr. Patrick Bowen, CEO and Co-Founder, Neurophos
“As the AI industry grapples with a surge in demand that tests our ability to satisfy with compute and power, disruptive approaches to compute may open routes to sustained or accelerated systems scaling that will be needed before the end of the decade. With their approach to hyper-efficient optical computation, the Neurophos team have advanced swiftly from a working proof of concept towards a realistic plan to deliver products on a timeline we can underwrite and believe in.”
Michael Stewart, Managing Partner, M12 (Microsoft’s Venture Fund)
