Markell Rawls

Markell Rawls is a Developer Advocate at Red Hat focused on llm-d and the future of LLM inference on Kubernetes. His background spans AI engineering and data science, with graduate work in Artificial Intelligence at the University of Pennsylvania and a Master of Applied Data Science from the University of North Carolina at Chapel Hill. He brings that foundation to helping engineers understand how to serve large language models efficiently at scale, from intelligent routing and prefix-cache-aware scheduling to disaggregated inference architectures. When he's not deploying models on OpenShift or building tutorials, you'll find him creating video walkthroughs and writing about the tools that make AI infrastructure actually work in production. Markell is passionate about open source and believes the best way to learn something is to deploy it yourself.