Shruti Koparkar

Shruti Koparkar is a senior manager of product marketing in the accelerated computing group at NVIDIA, focusing on AI inference. She has cross-functional experience spanning engineering, product management and product marketing — notably at Amazon Web Services and Arm. She holds a master’s degree in electrical and computer engineering from the University of Minnesota.

3 Published Articles

Posts by Shruti Koparkar

Leading Inference Providers Achieve Lowest Token Cost With Open Source Models on NVIDIA Blackwell

A diagnostic insight in healthcare. A character’s dialogue in an interactive game. An autonomous resolution from a customer service agent. Each of these AI-powered interactions is built on the same...

February 12, 2026

Mixture of Experts Powers the Most Intelligent Frontier AI Models, Runs 10x Faster to Deliver 1/10 the Token Cost on NVIDIA Blackwell NVL72

The top 10 most intelligent open-source models all use a mixture-of-experts architecture. Kimi K2 Thinking, DeepSeek-R1, Mistral Large 3 and others run 10x faster to enable one-tenth the cost per...

December 3, 2025

AWS, Google, Microsoft and OCI Boost AI Inference Performance for Cloud Customers With NVIDIA Dynamo

Editor’s note: This post is part of Think SMART, a series focused on how leading AI service providers, developers and enterprises can boost their inference performance and return on investment...

November 13, 2025

Shruti Koparkar

Posts by Shruti Koparkar

Leading Inference Providers Achieve Lowest Token Cost With Open Source Models on NVIDIA Blackwell

Mixture of Experts Powers the Most Intelligent Frontier AI Models, Runs 10x Faster to Deliver 1/10 the Token Cost on NVIDIA Blackwell NVL72

AWS, Google, Microsoft and OCI Boost AI Inference Performance for Cloud Customers With NVIDIA Dynamo

Explore the Best of GTC 2026 Sessions

National Robotics Week — Latest Physical AI Research, Breakthroughs and Resources

From RTX to Spark: NVIDIA Accelerates Gemma 4 for Local Agentic AI

Press Start on April: GeForce NOW Brings 10 Games to the Cloud

Efficiency at Scale: NVIDIA, Energy Leaders Accelerating Power‑Flexible AI Factories to Fortify the Grid

Share on Mastodon