The funding will be used to accelerate product development and expand go-to-market efforts, the companies said in a statement on Monday.
Founded in 2023, Tsavorite is building a full-stack AI compute platform spanning edge, enterprise, and data centre environments. Its core offering is an Omni Processing Unit (OPU), a chip architecture that integrates CPU, GPU, memory, and connectivity into a single system to improve performance and reduce data movement.
The startup claims its architecture can deliver up to 10x higher arithmetic intensity while improving power efficiency-an increasingly critical metric as enterprises scale AI workloads.
“Tsavorite is developing a differentiated, full-stack AI compute platform designed to address the growing need for power-efficient, scalable, and enterprise-ready systems,” said Sridhar Rampalli, managing partner at Pavestone. He added that the company has already secured early validation through strategic customers and ecosystem partnerships, including pre-orders worth $100 million.
Tsavorite also offers an integrated software layer-its Agentic Operating Stack (TAOS)-that enables developers to deploy AI models without rewriting code or relying on proprietary dependencies, positioning it as a vertically integrated alternative in the AI infrastructure stack.
“We are delighted to welcome Pavestone as our investment partner,” said Shalesh Thusoo, founder and chief executive of Tsavorite. “Their conviction in deep-tech innovation aligns closely with our vision as we scale next-generation AI compute hardware.”
Pavestone invests through its Rs 816-crore technology fund, which focuses on early growth-stage B2B startups with demonstrated product-market fit and enterprise adoption. The firm has been selectively backing companies working on foundational technologies across sectors.
Tsavorite operates across India and the US, with a design centre in Bengaluru playing a key role in its hardware and software development efforts. The company is currently working towards an advanced-node chip tape-out, signalling its ambitions to compete in the global semiconductor and AI compute market.