Jobs

Inferact is seeking a Member of Technical Staff, Cloud Orchestration to build the operational backbone for vLLM, ensuring reliable and scalable AI inference. This role involves designing systems for cluster management, deployment automation, and production monitoring across various cloud platforms and on-premise infrastructure. The ideal candidate will have strong experience with Kubernetes, custom operators, and managing GPU clusters, with a focus on making vLLM deployments observable, debuggable, and recoverable at massive scale. This is a fully remote position with competitive compensation and equity, aiming to accelerate AI progress by making inference cheaper and faster.