The era of the “Optical Processing Unit” (OPU) powering the next generation of AI infrastructure has arrived.
ALSO READ
From invisibility cloaks to AI chips: Neurophos raises $110M to build tiny optical processors for inferencing – Techcrunch
For years, we’ve known that AI is evolving faster than the hardware that supports it. Traditional silicon GPUs are hitting a wall, and consuming massive amounts of energy and generating heat that data centers can no longer manage.
2026 is the demarcation line where AI infrastructure technology changes to photonics. It’s imperative in order to unlock the true value and global scale of artificial intelligence, and it’s going to be powered by light.
We’re thrilled to share that Neurophos has closed its Series A funding round, and our follow-on participation from our Series Seed investment. The Series A round led by Gates Frontier and Microsoft’s M12 is to scale what might be the most significant “physics-level” breakthrough in a decade: The OPU Photonic AI Chip.
Here is why the industry is buzzing about Neurophos:
100x More Efficient: By using light (photons) instead of electricity to perform calculations, these chips deliver up to 100x the performance and energy efficiency of traditional silicon.
The 10,000x Shrink: Their team has achieved the “impossible”—shrinking optical components by 10,000x to pack over 1 million processing elements on a single chip.
Sustainable Scaling: This isn’t just about speed; it’s about the planet. This technology slashes the carbon footprint of AI, allowing us to scale intelligence without crashing the power grid.
“Drop-in” Ready: No need to rebuild the rack. OPUs are designed to seamlessly replace existing GPUs.
With a powerhouse team featuring veterans from NVIDIA, Apple, Meta, and Intel, Neurophos isn’t just predicting the future of compute—they’re building it.
Neurophos, a leader in photonic AI chip technology, has raised $110 million in an oversubscribed Series A round, bringing total funding to $118 million. The round 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 others.
“Modern AI inference demands monumental amounts of power and compute,” said Dr. Marc Tremblay, Corporate Vice President and Technical Fellow of Core AI Infrastructure at Microsoft. “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.”
As AI adoption accelerates, data centers face critical limitations in power and scalability. Traditional silicon-based GPUs cannot meet growing computational demands, resulting in increased costs and energy consumption. Neurophos addresses these challenges with a proprietary optical processing unit (OPU) that integrates over one million micron-scale optical processing elements on a single chip. This innovation delivers up to 100x the performance and energy efficiency of current leading chips, offering a practical, drop-in replacement for GPUs in data centers.
“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,” says 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.”
Neurophos’ breakthrough lies in the development of micron-scale metamaterial optical modulators—a 10,000x miniaturization over previous photonic elements—making large-scale, manufacturable photonic computing possible for the first time. The result is a new class of AI accelerator: ultra-fast, energy-efficient, and adaptable to future AI workloads.
“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,” said Michael Stewart, Managing Partner at M12, Microsoft’s Venture Fund.
“From the start, we backed Neurophos because we believed the future of AI was bound by physics, not by algorithms,” said Chris Alliegro, Managing Partner at MetaVC Partners. “Neurophos is addressing the only problem that really matters for the future of AI: the limits imposed by silicon. Their optical architecture provides the foundation for the next generation of machine intelligence.”
Neurophos’ technology enables significant reductions in power consumption, supporting the next generation of AI infrastructure without the need for exponential increases in energy or physical resources. The company’s advancements promise to make AI more accessible and cost-effective across industries.
“Reducing chip-related emissions is now as essential as delivering compute,” said Jonathan Goldberg, CEO of Carbon Direct Capital. “Neurophos offers step-function gains in both. This is the kind of next-generation AI infrastructure companies urgently need as their compute demands skyrocket.”
The new funding will accelerate delivery of Neurophos’ first integrated photonic compute system, including datacenter-ready OPU modules, a full software stack, and early-access developer hardware. The company is expanding its Austin headquarters and opening a San Francisco engineering site to meet early customer demand.
Additional investors include DNX Ventures, Geometry, Alumni Ventures, Wonderstone Ventures, MetaVC Partners, Morgan Creek Capital, Silicon Catalyst Ventures, Mana Ventures, Gaingels, and others. Cooley LLP serves as legal counsel.
About Neurophos
Neurophos Inc. is an Austin-based semiconductor company developing high-performance, energy-efficient photonic AI inference chips. Founded by Dr. Patrick Bowen and Dr. Andrew Traverso, the team includes industry veterans from NVIDIA, Apple, Samsung, Intel, AMD, Meta, ARM, Micron, Mellanox, Lightmatter, and more. For details, visit www.neurophos.com.