Saurav Agarwal

Saurav Agarwal

Solutions Architecture and Engineering

NVIDIA

Saurav is an AI leader with 14 years of experience in Generative AI, Big Data Engineering, and Cloud Computing. He specializes in NVIDIA’s AI stack, delivering scalable solutions in LLMs, Conversational AI, and Data Science. Known for driving digital transformation across sectors, Saurav excels at building accurate, scalable, and reliable AI systems. His strategic focus empowers organizations to harness the full potential of GenAI, accelerating innovation and business growth through cutting-edge technology.

Build, Evaluate, and Optimize Full-Stack AI Agent Systems for Real-World Applications

Agentic AI systems, which are complex workflows that integrate multiple AI agents, are becoming essential for organizations aiming to automate intricate processes, improve decision-making, and provide seamless digital experiences. NVIDIA Agent Intelligence is an open-source toolkit designed to simplify, optimize, and accelerate the development and evaluation of robust, full-stack agentic AI solutions.

In this session, you'll gain an in-depth understanding of NVIDIA Agent Intelligence toolkit and how to leverage its powerful features to connect, evaluate, and scale your AI agent teams. We'll explore how it simplifies development, enables fine-grained telemetry for enhanced performance, and facilitates detailed accuracy assessments of agentic workflows. Discover how to rapidly prototype AI agent systems, integrate the generative AI pipeline.

Read More

Managing and scaling ML workloads have never been a bigger challenge in the past. Data scientists are looking for collaboration, building, training, and re-iterating thousands of AI experiments. On the flip side ML engineers are looking for distributed training, artifact management, and automated deployment for high performance

Read More

Managing and scaling ML workloads have never been a bigger challenge in the past. Data scientists are looking for collaboration, building, training, and re-iterating thousands of AI experiments. On the flip side ML engineers are looking for distributed training, artifact management, and automated deployment for high performance

Read More