Austin-based Neurophos has closed a $110 million oversubscribed Series A financing to accelerate development of its photonic AI inference processors, bringing total funding to $118 million. The round was led by Gates Frontier with participation from M12, Carbon Direct Capital, Aramco Ventures, Bosch Ventures, Tectonic Ventures, Space Capital, and others. The company plans to use the capital to move its optical processing unit (OPU) from prototype toward data-center-ready systems.
Neurophos is targeting a core constraint facing large-scale AI infrastructure: power and scalability limits of silicon GPUs. Its approach replaces electronic matrix-multiply engines with an optical architecture that integrates more than one million micron-scale optical processing elements on a single chip. The company positions the OPU as a drop-in alternative for AI inference workloads, with claims of up to 100× gains in performance per watt compared with leading GPU platforms.
The technical foundation centers on metamaterial optical modulators miniaturized by roughly 10,000× versus prior photonic elements, enabling dense, manufacturable photonic compute at scale. Neurophos says this level of integration allows efficiency and throughput to scale together, avoiding the power density ceilings that increasingly shape data-center design. The funding will support delivery of OPU modules, a full software stack, early-access developer systems, and expansion of engineering operations in Austin and San Francisco.
- $110 million Series A led by Gates Frontier; total funding reaches $118 million
- Participation from M12 (Microsoft’s venture fund), Carbon Direct Capital, Aramco Ventures, Bosch Ventures, and others
- Optical processing unit integrates over one million micron-scale photonic elements on a single chip
- Focus on AI inference acceleration with significant reductions in power consumption
- Roadmap includes data-center-ready OPU modules, software stack, and developer hardware
“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,” said Dr. Patrick Bowen, CEO and co-founder of Neurophos. “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.”
