Fabless semiconductor startup optoML raises $1.8 million to scale up hiring, work on next-gen chips

Fabless semiconductor startup optoML has raised $1.8 million in a pre-Series A funding round led by deeptech VC Bluehill & A99.

The startup will use the raised funds for scaling up hiring and start work on next generation chips as tape out with TSMC is completed. The transaction will be completed pending regulatory approval.

Founded by Saravana Maruthamuthu, optoML brings scalable Analog-in-Memory Compute with optical interconnects, designed to scale from edge deployments to hyperscalers, targeting higher energy efficiency and lower latency with reduced silicon area and thereby lower cost.

This investment comes after optoML signed an MoU with Kaynes Semicon to support assembly and testing once the wafers arrive from TSMC, accelerating the journey from silicon to scalable packaging, manufacturing, and product readiness.

The startup has also completed 12nm TSMC tapeout realizing its core AiMC architecture and SoC integration path.

Manu Iyer, General Partner, Bluehill.VC, said, “India’s deep-tech ecosystem is really coming into its own and semiconductors is an area where we are seeing fantastic progress. optoML, a fabless semicon company, sits at the intersection of two irreversible shifts in compute — analog in-memory compute architectures and optical interconnects. As AI workloads scale from the edge to hyperscalers, energy efficiency, latency, and bandwidth are becoming first-order constraints. optoML’s 12nm tapeout with TSMC and its partnership with Kaynes Semicon mark a critical transition from research to real silicon and scalable production. We believe this is the kind of deep-tech platform that can meaningfully reshape the cost and efficiency curve of AI infrastructure. And these frugal innovations with a clear commercial use case will define India’s global AI dominance.”

Vignesh S, General Partner of a99 said, “We at a99 are thrilled to invest and be a part of the optoML juggernaut. As AI workloads move to the edge, power efficiency becomes the real constraint. optoML’s analog-in-memory approach is designed to address exactly that  shifting how AI inference can be delivered at lower energy and cost. We believe foundational semiconductor IP in AI infrastructure will matter a lot over the next decade, and this is a step in that direction for our investment thesis at a99.”