AI inference at the edge using OpenShift AI
Red Hat AI: What’s new and what’s next, from production inference to autonomous agents
John Hurlocker, Senior Principal Architect, and Trevor Royer, Senior Architect, discuss the critical challenges organizations face when running LLM inference workloads - specifically the ROI Trap, architectural complexity, and silent performance failures.
John Hurlocker is a Senior Principal Architect in Red Hat’s Global Services AI Practice and has been with Red Hat since 2004, helping organizations adopt and scale technologies across middleware, business automation, and enterprise platforms. More recently, John has focused on helping customers build the foundational platforms and processes needed to move AI models from experimentation into secure, scalable production environments.
Trevor Royer is a Senior AI Platform Specialist Solution Architect in Red Hat's AI Platform team where he helps customers understand and adopt Red Hat's AI technologies. Trevor has been with Red Hat since 2021 where he helped establish Red Hat's North America Services AI Practice. There, he helped customers turn ideas for predictive models and LLMs into practical and scalable solutions that solve business problems.