Senior GPU Compute Cluster Engineer

Inferact Inc. is building a world-class GPU compute platform powering vLLM. We seek a hands-on cluster administration engineer to own the high-performance infrastructure that keeps our engineers productive. You will monitor GPU servers, manage scheduling with SLURM/Kubernetes, automate operations with Bash and Python, and respond to incidents end-to-end across multi-provider deployments. This San Francisco–based, remote-friendly role offers strong compensation and equity for engineers who thrive #J-18808-Ljbffr Inferact Inc.