Senior AI Data Center Network Engineer
Posted Updated
Description
You will architect, deploy, optimize, and operate high-performance networks for large GPU clusters. You will investigate complex network issues, automate configuration management, monitor fabric health, support container and hybrid-cloud networking, and lead network changes, incident response, mitigations, and root-cause analysis.
Responsibilities
- Architect scalable, highly available AI data center network solutions
- Design, deploy, and optimize GPU-cluster InfiniBand and RoCEv2 fabrics
- Configure and manage NVIDIA Spectrum and Quantum switches
- Investigate network issues involving RDMA, packet loss, congestion, latency, and NCCL timeouts
- Develop network automation using Python, Ansible, and Terraform
- Monitor network telemetry and fabric health using UFM, NetQ, Zabbix, and Prometheus
- Support Kubernetes, Docker, and hybrid-cloud network integration
- Lead network changes, capacity expansions, firmware upgrades, incident response, and root-cause analysis
Requirements
- Bachelor's degree or above in a related field
- 8-10 years of large-scale data center network engineering, architecture, or operations experience
- Expertise in TCP/IP, BGP, OSPF, ISIS, VXLAN EVPN, and Spine-Leaf networking
- Experience with InfiniBand, Subnet Manager, RoCEv2, PFC, ECN, and congestion control
- Experience configuring Cisco Nexus, NVIDIA/Mellanox, or Juniper network equipment
- Network automation and scripting skills in Python, Ansible, and Terraform
- Linux system-administration skills
- Experience with Kubernetes CNI and cloud-native architectures
- Professional fluency in English and Chinese