Enlightra, a deeptech startup developing chip-scale multiwavelength lasers for next-generation data transmission, has raised a total of $15 million. Investors include Y Combinator, Runa Capital, Pegasus Tech Ventures, Protocol Labs, Halo Labs, Asymmetry Ventures, and TRAC VC, among others.
Modern AI training increasingly depends on faster connections between GPUs, yet many systems still rely on copper links constrained by bandwidth and power consumption. As AI clusters and data centres scale, these limitations are becoming more pronounced.
Enlightra’s approach uses multiwavelength lasers that consolidate many discrete lasers into a single integrated source, reducing power use, cost, and physical footprint. Each wavelength functions as an independent data channel, enabling multiple high-bandwidth connections from one laser source and supporting a shift from copper wiring to compact optical links.
The world’s AI infrastructure is hitting the limits of copper. Our lasers unlock a new level of energy-efficient connectivity by turning light into the backbone of GPU communication,
said Maxim Karpov, co-founder and co-CEO of Enlightra.
Using additional wavelengths allows optical fibre networks to operate closer to their full capacity, co-founder and co-CEO John Jost explained.
Our technology enables AI clusters and data centres to scale more efficiently by decoupling performance growth from energy and cost increases.
Built using industry-standard silicon photonics fabrication processes, the lasers are designed for large-scale manufacturing, enabling production at volumes suitable for global data centre deployment. The company has developed 8- and 16-channel lasers aligned with customer requirements for AI chip interconnects and reports error-free data transmission at target speeds and power levels. Pilot production is planned for 2027.
The company’s vision extends beyond AI clusters. Its scalable comb-laser platform could power future optical links across entire data centres, subsea cables, and even chip-to-memory interconnects, with potential applications in quantum and space-based communications.
The funding will support Enlightra’s next steps to improve data-transfer speed and energy efficiency for AI infrastructure.
Would you like to write the first comment?
Login to post comments