Volantis raised $88M Series A funding to scale its photonic-based AI inference system targeting cost and power efficiency.

Volantis, a San Francisco semiconductor company developing a new category of AI inference system, announced an $88 million Series A on October 1, 2026, co-led by Lachy Groom and Abstract Ventures. The round also drew participation from John Doerr, VXI Capital, Triatomic and Susa Ventures, with angel investors Dwarkesh Patel, Naveen Rao and Sholto Douglas joining. The financing brings Volantis's total funds raised to $97 million, including backing from Sam Altman, Jeff Dean, Dylan Patel and John Doerr, among others.

The new capital will support development and commercialization of the A-1 system and its photonic memory architecture, including expanding the engineering team and moving toward customer deployments. Volantis plans to deliver its first integrated inference engines to customers in 2027.

Chief executive and co-founder Tapa Ghosh said current hardware forces a tradeoff between running the largest, most sophisticated models and running them fast. Volantis was started to eliminate that tradeoff. As AI agents take on more work, execution speed will increasingly determine how fast companies can operate, Ghosh added.

Volantis identifies a memory wall in current AI hardware: on-chip SRAM provides high bandwidth but limited capacity, constraining model size and context windows while increasing cost and energy consumption, while GPUs and other HBM-based systems provide greater capacity but see bandwidth limit performance with increasingly large models. Newer approaches such as 3D DRAM remain on the same tradeoff curve.

The A-1 system is designed to increase memory capacity and bandwidth simultaneously by nearly two orders of magnitude. It will run models exceeding 20 trillion parameters at up to 10,000 tokens per second per user while reducing inference cost per token. As one example, this performance could let a coding agent complete a task in two minutes instead of 30, giving developers more opportunities to test and iterate.

Volantis lists the following A-1 specifications: 10 TB of memory capacity, 240 TB/s of memory bandwidth, a 20kW power envelope, 10 TB/s of off-wafer IO bandwidth and a 15U form factor designed to fit existing datacenter racks. The first product integrates licensed, silicon-proven compute engine IP from external parties with proprietary photonics developed over four years. According to the company, A-1 delivers 15 times better tokens per dollar than NVIDIA Rubin, six times better tokens per watt for low-latency mixture-of-experts models above one trillion parameters, and more than 30 times lower latency for large-model inference.

Volantis has developed a new category of photonic interconnect designed specifically to connect compute chips to memory. Its optical fabric connects large numbers of memory chips into a unified pool, aggregating their bandwidth as capacity expands. This allows A-1 to grow capacity and bandwidth together while using lower-cost off-chip memory. While photonics already moves data inside data centers, chip-to-memory connections require more than 100 times as much data to travel over much shorter distances, creating different energy and cost requirements.

Volantis built its photonic platform using custom micro-VCSELs rather than external lasers, drawing on the existing gallium arsenide VCSEL supply chain and avoiding indium phosphide supply constraints. The micro-VCSELs are small, temperature-stable and low power, enabling end-to-end links consuming less than one picojoule per bit.

The company's links run at 24G per lane with sub-five-nanosecond latency, scaling to tens of thousands of lanes for more than 200 TB/s of aggregate bandwidth. Integrated waveguides are more than 2,500 times smaller than optical fiber. While electrical interconnects reach roughly two to five millimeters, the company's optical waveguides reach beyond 200 millimeters, allowing more than 220 memory chiplets to be connected in a single uniform-latency memory pool. The links remain thermally stable above 95 degrees Celsius with a bit error rate below 1e-12 at wafer scale, and the design is described as the world's first optical interposer with no external lasers.

Volantis's founding team includes semiconductor and photonics veterans from NVIDIA, AMD, Broadcom and Ayar Labs. Co-founder and chief technology officer Roy Meade led Micron's HBM program and previously served as vice president at Ayar Labs. Director of packaging Inderjit Singh built the industry's first CoWoS product. Vice president of engineering Daniel Klowden built the world's first processor with direct optical communication. Director of laser engineering Chris Chase brought a new VCSEL laser category to volume production. CEO Tapa Ghosh is a Thiel Fellow and former Y Combinator founder with four patents.

The company's backers include OpenAI chief executive Sam Altman, Google chief scientist Jeff Dean, SemiAnalysis founder Dylan Patel, Meta chief AI officer Alex Wang, Kleiner Perkins chairman John Doerr, AngelList founder Naval Ravikant, Hugging Face co-founder Thomas Wolf, Y Combinator co-founder Trevor Blackwell and OS Fund founder Bryan Johnson.

Volantis plans to unveil additional innovations behind the architecture as the A-1 moves toward commercialization.