Ritika Borkar

Ritika Borkar is a principal architect and senior manager at NVIDIA, driving model/hardware co-design to improve the efficiency of serving generative AI. Over her long tenure at NVIDIA, she has worked across multiple layers of the stack to optimize deep learning performance and efficiency, and has also been part of the MLPerf teams behind several top-ranking MLPerf benchmark submissions. Ritika also serves on the board of MLCommons, working toward the mission of making better, more accessible AI for everyone. She holds a master’s in electrical engineering from the University of Minnesota, Twin Cities.
Avatar photo

Posts by Ritika Borkar

Developer Tools & Techniques Jul 31, 2026

Co-Designing AI Model Attention for Fast, Interactive Long-Context Inference

As agentic and long-context workloads become common, the context lengths increase and attention consumes a larger share of inference time (Figure 1). Because... 14 MIN READ
Agentic AI / Generative AI Jul 10, 2026

AI Model Co-Design: Hardware-Friendly LLM Design

AI performance comes down to three dimensions:  Accuracy: How well the model reasons and produces outputs Throughput: How many tokens per second a... 17 MIN READ
Data Center / Cloud Jun 06, 2025

How NVIDIA GB200 NVL72 and NVIDIA Dynamo Boost Inference Performance for MoE Models

The latest wave of open source large language models (LLMs), like DeepSeek R1, Llama 4, and Qwen3, have embraced Mixture of Experts (MoE) architectures. Unlike... 12 MIN READ