TensorWave
Senior Staff Infrastructure Engineer - Virtualization
Remote · Remote · Senior Staff · Full-time · Posted May 14, 2026
- Experience
- 7+ years; no alternatives stated.
- Visa sponsorship
- Offers are contingent upon verification of identity and authorization to work in the United States, as required by law.
About the job
Leads the design, implementation, and operation of a scalable KVM/QEMU virtualization platform for high-performance, GPU-intensive infrastructure across multiple data centers.
What you'll do
- Design and evolve virtualization architecture, including migration from existing platforms toward KVM/QEMU.
- Define VM lifecycle, performance isolation, resource allocation, and resilience standards; optimize for CPU, NUMA, PCIe, and GPU workloads.
- Automate hypervisor deployment and lifecycle management, troubleshoot system-level performance, and collaborate with networking and storage teams.
What they ask for
- 7+ years of experience in infrastructure, systems engineering, or platform engineering.
- Deep Linux virtualization experience, including KVM/QEMU and libvirt or similar tooling.
- Experience designing and operating virtualization platforms at scale (hundreds+ hosts), plus infrastructure automation (e.g., Ansible, Terraform, or similar).
- Strong understanding of CPU scheduling, NUMA, memory management, storage I/O, Linux networking, and high-performance networking; strong distributed-systems troubleshooting skills.
Nice to have
- Experience in cloud or CSP environments; familiarity with GPU workloads and passthrough (VFIO), SR-IOV, Kubernetes, or bare metal provisioning.
- Exposure to distributed storage systems or high-performance/low-latency environments.
Tools
KVM/QEMU, libvirt, Ansible, Terraform, Proxmox, SR-IOV, RDMA, VFIO
AI focus
Builds infrastructure to support AI workloads, including GPU-intensive environments.
Model-written summary · the original posting is authoritative