Senior Infrastructure Engineer — IDC / Bare-Metal Kubernetes

Design rack layout, network topology, and overall configuration for colocation

Design and implement an isolated Out-of-Band (OOB) management network (BMC, IPMI, Redfish) with full security hardening

Coordinate with colocation and hardware vendors — servers, switches, cross-connects, uplinks, remote hands, and cage/rack administration

Build bare-metal automation for fleet-wide zero-touch OS provisioning (MAAS / Tinkerbell / Cluster API)

Set up production-grade self-hosted Kubernetes clusters from scratch and maintain the core stack: Cilium (CNI), GitOps (ArgoCD), etc.

Own cluster lifecycle: upgrades, scaling, node maintenance, incident response

Write SOPs, runbooks, and post-mortems; participate in 24×7 on-call rotation

Establish hybrid-cloud interconnect between IDC and public cloud (VPN / Direct Connect / peering)

Pave the way for scale-out: GPU workloads (NVIDIA GPU Operator, passthrough, MIG) and VM workloads running alongside containers (KubeVirt or similar)

5+ years in data center / infrastructure / platform engineering

Hands-on experience building physical infrastructure from scratch: rack layout, network topology, server commissioning, and coordinating cross-connects and remote hands with colo / vendors

Practical experience designing and operating OOB management networks (BMC, IPMI, Redfish)

Have stood up production-grade self-hosted Kubernetes from scratch, and can independently debug cluster-level issues (CNI, CSI, storage)

Strong Linux systems administration and performance tuning (kernel, networking, storage I/O)

Bare-metal automation experience with at least one of: MAAS, Tinkerbell, Cluster API

Proficient with Terraform, Ansible, and at least one scripting language (Python / Go / Bash)

Experience with Cisco network and related techniques (VLAN, LACP/LAG, BGP, ACL, etc)

Experience with Palo Alto firewall configuration

Experience with storage systems (NetApp, Dell EMC, Pure Storage)

Fluent in English or Mandrain

High-density racks (30kW+) and 400G+ networking experience

Familiarity with immutable OS (Talos Linux / Flatcar / Bottlerocket)

Proficiency across both AWS and GCP; cross-cloud data migration experience

Experience building storage or Bigdata / offline data clusters

Virtualization experience (KubeVirt or similars)

Exposure to NVIDIA GPU Operator and K8s GPU workloads

CKA / CKS certification

CCNP / CCIE certification

Professional-level Japanese