Learn how to scale real-time model serving with GPU optimization, dynamic batching, and latency tuning to maximize ML inference performance
FEB 12, 2026|8 min read
Goutam Murlidhar
Goutam Murlidhar is a Senior Software Engineer at Snowflake, dedicated to scaling the performance of the company’s Model Serving Infrastructure. In this role, he focuses on optimizing critical inference metrics, driving improvements in latency, throughput, and utilization across the platform. His work supports the full spectrum of AI workloads hosted on Snowflake, ranging from efficient embedding models to complex Large Language Models (LLMs). Through these contributions, he ensures that Snowflake delivers the high-performance foundation necessary for efficient and reliable AI at scale.
