
Volantis, a semiconductor company developing technology for AI inference, has raised $88 million in Series A funding to develop and commercialize its new AI computing architecture.
The round was co-led by Lachy Groom and Abstract Ventures, with participation from John Doerr, VXI Capital, Triatomic, and Susa Ventures. Angel investors Dwarkesh Patel, Naveen Rao, and Sholto Douglas also joined the round.
Volantis plans to use the funding to expand its engineering team, develop its first system, A-1, and move the technology toward customer deployments.
The company is developing A-1 to address a key challenge in AI inference: balancing memory capacity and bandwidth. Volantis says its system is designed to run AI models with more than 20 trillion parameters at speeds of up to 10,000 tokens per second per user, while also aiming to reduce inference costs.
Volantis is using photonic interconnect technology to connect computing chips with large pools of memory. The company says this approach could allow memory capacity and bandwidth to increase together, helping AI systems process larger models at higher speeds.
The company was founded by semiconductor and photonics engineers with experience at NVIDIA, AMD, Broadcom and Ayar Labs. The team has previously worked on technologies including CoWoS packaging, tunable VCSELs and silicon photonics systems.
Volantis said its technology could support faster AI applications, including AI agents that need to process complex tasks and generate responses quickly.
The company plans to deliver its first integrated AI inference engines to customers in 2027. The new funding will support product development, commercialization and the continued development of its photonic memory architecture.