Diya Shah

Diya Shah is a machine learning engineer at Sarvam AI, working on inference and optimization of models to drive maximum efficiency in serving stacks. By targeting accelerations at the system and kernel level, she works to ensure that large-scale models remain performant on diverse hardware environments. Diya has a bachelor of technology in electronics and communications engineering from the LNM Institute of Information Technology (LNMIIT) in India.
Avatar photo

Posts by Diya Shah

Agentic AI / Generative AI

How NVIDIA Extreme Hardware-Software Co-Design Delivered a Large Inference Boost for Sarvam AI’s Sovereign Models

As global AI adoption accelerates, developers face a growing challenge: delivering large language model (LLM) performance that meets real-world latency and cost... 15 MIN READ