Anish is an engineering manager at Red Hat in the Inference Engineering organization. He is currently working on making efficient distributed inference on Kubernetes at reality via llm-d. He has been working in the machine learning on Kubernetes space for the last 7 years across the entire spectum from model customization through serving. This has been via projects such as Kubeflow, Ray, Kueue, and Kserve, to name a few.
