Senior Solutions Architect – AI Infrastructure Networking
Core
Design and publish network reference architectures and solution designs for k0rdent AI, covering data center topologies from a single rack to multi-thousand-GPU clusters.
Role type
Senior Solutions Architect (AI Infrastructure Networking)
Builds
Reference architectures, working code, proofs of concept, and automation tooling for GPU clouds and AI factories.
Domain
AI Infrastructure Networking / Data Center Networking
Deliverable
production ML models
Required skills
Data center network design (spine-leaf, Clos, rail-optimised fabrics), InfiniBand (subnet management, partitioning, NCCL/RDMA), RoCEv2 on Ethernet (PFC, ECN, DCQCN), Routing and overlays (BGP, EVPN-VXLAN, VRF), Linux networking (NICs, PCI passthrough, SR-IOV, IOMMU, NUMA), Kubernetes networking (CNI, Multus, SR-IOV, RDMA device plugins), Virtualisation on Kubernetes (KubeVirt), Programming/Scripting (Python, Go), Infrastructure as Code (Terraform, Ansible, Helm)
Preferred skills
NVIDIA networking (Quantum, Spectrum-X, ConnectX, BlueField DPUs), GPU cloud/HPC operator experience, Bare-metal provisioning (Metal3, Ironic, Redfish), Network automation and SDN controllers (Cumulus Linux, SONiC)
Responsibilities
Design compute fabrics on InfiniBand and RoCEv2 Ethernet; Define front-end, storage, and management networks; Specify multi-tenant isolation across the stack; Prototype alternative designs in the lab; Build and run proofs of concept with customers and partners; Write automation and tooling for reproducible architectures; Present at industry events and run hands-on workshops.
Seniority
Senior, hands-on IC with research and outward-facing responsibilities