Presentation: Realtime and Batch Processing of GPU Workloads (opens in new tab)

Joseph Stein discusses engineering an enterprise AI-as-a-Service platform within a private cloud data center. He explains how to maximize underutilized GPU pools via multi-namespace scheduling, leverage Valkey and Lua for atomic priority queuing and backpressure management, mitigate OWASP Top 10 LLM risks via central proxy gateways, and scale batch pipelines using a custom S3-to-Kafka proxy.