Roy Belio is a Software Engineer at Red Hat, focused on AI/ML infrastructure and open source LLM tooling. He works on building proof-of-concept deployments that bridge open source AI models with cloud-native platforms, contributing to projects like llama-stack and driving integration across inference, fine-tuning, and orchestration stacks including vLLM, KServe, and MLflow on Red Hat OpenShift.
Before Red Hat, Roy spent time at Microsoft. He holds a background in computer science and cyber security, he brings a pragmatic, ship-it approach to making AI workloads production-ready on Kubernetes. When he's not deploying models, he's likely climbing mountains or crowd surfing.
Explore how Red Hat OpenShift AI was used to run an unsupervised AI agent for 24 hours, improving validation loss by 2.3% without human intervention. Learn about the container build, Kubernetes deployment, and key findings.
