Description
Inferact is hiring a Cloud Orchestration Engineer to build the operational backbone for vLLM at massive scale. The role focuses on cluster management, deployment automation, production monitoring, observability, debugging, and recovery of AI model deployments. The engineer will work with Kubernetes, custom operators, Python/Rust/Go, infrastructure-as-code, GPU clusters, and cloud or on-premise infrastructure, with experience in ML orchestration and GPU scheduling preferred. The position is based in Singapore and offers S$200,000 to S$400,000 annually plus equity, medical, dental, and vision coverage, and case-by-case visa sponsorship.
