Description
Gcore is hiring a DevOps Engineer for its AI Inference Operations Team to design, deploy, and maintain infrastructure and services supporting scalable, secure AI inference workloads in on-premises environments. The role focuses on GPU scheduling, model deployment pipelines, data access patterns, monitoring, observability, system architecture, and performance testing. Candidates should have strong Kubernetes, Linux, networking, automation, infrastructure-as-code, monitoring, and CI/CD experience, with additional exposure to GPU, HPC, or cloud environments preferred.
