Site Reliability Engineer - ARK Large Model Platform (Singapore)

Build and operate the ARK Large Model Platform on VolcanoEngine, focusing on stability across control and data planes for large-scale model systems. You will implement DevOps practices, develop observability for monitoring reliability and performance, and manage super large-scale clusters to ensure efficient operations and maintenance. The role also involves researching solutions for large model deployments and supporting a cloud-native infrastructure stack used for high-performance inference.