Sponsor Talk
Ravi Mahatme, Senior Director of Product at Celestial AI
Title: Photonic Fabric: Optical Scale-Up Networks for Accelerated Computing
Abstract:
As large AI models with reasoning capabilities and new paradigms like inference-time compute and agentic AI proliferate, traditional data center infrastructure is strained to its limits. The fundamental unit of compute is evolving from a few XPUs in a server to tens of XPUs in a rack to a cluster of thousands of XPUs across multiple racks. Traditional copper-based interconnects are reaching their limits and are unable to scale without incurring excessive power and costs.
The Photonic Fabric™ is a revolutionary optical interconnect technology for scale-up networks that enables continued scaling in AI data center compute by delivering very high bandwidth at nano-second latencies with in-network high-performance, high capacity memory and in-network computing.
In this presentation, we will talk about Photonic Fabric technology and how optical connectivity chiplets and scale-up system products based on the Photonic Fabric can deliver the next generation of AI infrastructure.
The Photonic Fabric™ is a revolutionary optical interconnect technology for scale-up networks that enables continued scaling in AI data center compute by delivering very high bandwidth at nano-second latencies with in-network high-performance, high capacity memory and in-network computing.
In this presentation, we will talk about Photonic Fabric technology and how optical connectivity chiplets and scale-up system products based on the Photonic Fabric can deliver the next generation of AI infrastructure.
Biography:
Ravi Mahatme is the Senior Director of Product at Celestial AI, where he leads product strategy and development across hardware, systems, and software for next-generation AI infrastructure built on Celestial’s proprietary Photonic Fabric technology. His work focuses on solving data movement and scalability challenges in modern AI workloads.
Prior to joining Celestial AI, Ravi was part of the AWS SageMaker team, where he built foundational tools for distributed AI training and inference, including SageMaker Profiler.
Ravi spent over 17 years at Arm, transitioning from engineering to global product leadership roles. His experience spans semiconductor IP, high-performance CPU implementation, and neural processing units (NPUs)—giving him deep insight into the full AI compute stack.
He has extensive experience working with customers across North America, Europe, and APAC, and is widely recognized for his strategic and technical expertise in the AI ecosystem.
Ravi holds an M.S. in Computer Engineering from North Carolina State University and a B.E. in Electronics from Mumbai University.
Prior to joining Celestial AI, Ravi was part of the AWS SageMaker team, where he built foundational tools for distributed AI training and inference, including SageMaker Profiler.
Ravi spent over 17 years at Arm, transitioning from engineering to global product leadership roles. His experience spans semiconductor IP, high-performance CPU implementation, and neural processing units (NPUs)—giving him deep insight into the full AI compute stack.
He has extensive experience working with customers across North America, Europe, and APAC, and is widely recognized for his strategic and technical expertise in the AI ecosystem.
Ravi holds an M.S. in Computer Engineering from North Carolina State University and a B.E. in Electronics from Mumbai University.