Inferact is seeking a hands-on cluster administration engineer to own and operate high-performance GPU compute infrastructure. You will ensure health, availability, and observability of clusters across neo-cloud and dedicated providers, enabling engineers to build, test, and improve vLLM-powered systems.
You will manage GPU servers, driver health, scheduling, and incident response, partnering with leadership to standardize provisioning and debugging while expanding compute capacity for fast AI
#J-18808-Ljbffr
Contact Details:
INFERACT SINGAPORE PTE. LTD. Recruitment Team
