DevOps Engineer – AI Inference Platform

About the role

Gcore is seeking a DevOps Engineer to design, deploy, and maintain the infrastructure that powers AI inference workloads on‑premises. You will work with cutting‑edge GPU hardware and collaborate with ML engineers to ensure scalable, secure, and high‑performance AI services.

Key responsibilities

• Design and operate infrastructure for AI inference, including GPU scheduling, model deployment pipelines, and data access patterns.
• Build and maintain monitoring, observability, and alerting solutions (dashboards, runbooks) for model health and system performance.
• Collaborate with ML engineers and platform teams to define system architecture, integrate inference runtimes, and test performance at scale.
• Develop automation and operational tooling using Python, Go, or Bash.

Required profile

• Strong understanding of Kubernetes architecture (CNI, CSI, operators, ingress/gateway, control plane).
• Hands‑on experience operating and troubleshooting production Kubernetes clusters.
• Deep Linux and networking troubleshooting skills (DNS, routing, firewalling, TLS, MTU, connectivity).
• Experience with infrastructure‑as‑code tools such as Terraform or Ansible.

Required skills

• Kubernetes
• Python, Go, Bash
• Terraform or Ansible
• VictoriaMetrics / Grafana
• Git‑based workflows and CI/CD pipelines
• Linux system administration
• Network troubleshooting (DNS, routing, TLS, MTU)

What we offer

• Opportunity to work with leading technology partners (Intel, NVIDIA, Dell, Equinix).
• Access to a global infrastructure with 210+ edge locations and thousands of GPUs.
• Collaboration within a fast‑growing, international team of 550+ professionals.