Jobs

Inferact is seeking a hands-on Cluster Administration Engineer to own and operate their high-performance GPU compute infrastructure, ensuring its health, availability, and usability around the clock. This role involves taking ownership of cluster health, GPU availability, monitoring, scheduling, and incident response across critical systems. The ideal candidate will have experience administering large compute clusters, strong Linux fundamentals, and expertise in operating GPU servers and cluster scheduling tools like SLURM or Kubernetes. Your work will directly impact Inferact's ability to build, test, and improve the systems powering vLLM, accelerating AI progress.