Staff Cloud Hypervisor Engineer, Compute
Core
Lead architect for next-generation virtualization stack to deliver bare-metal performance for massive-scale GPU fleets and AI/ML workloads.
Role type
Staff Cloud Hypervisor R&D Engineer
Builds
Next-gen hypervisor environment with GPU/DPU first-class support and hardware pass-through
Domain
AI Infrastructure / Cloud Virtualization / Low-level Systems
Deliverable
production ML models
Required skills
Hypervisor internals, Kernel development, Low-level systems programming, CPU virtualization, Memory virtualization, Hardware-Software integration, C, C++, Rust, QEMU, KVM, Linux kernel debugging, VirtIO, vhost-user
Preferred skills
Rust for modern systems programming, Hardware engineering background
Technologies
KVM, QEMU, Rust, C, C++, Linux kernel, SR-IOV, VFIO, mdev, NVIDIA GPUs, BlueField DPUs, InfiniBand, RoCE, PCIe
Responsibilities
Lead R&D and implementation of core hypervisor components optimized for GPU fleets, Develop hardware pass-through techniques for near-zero latency, Solve high-stakes challenges like live migration for large VRAM workloads, Conduct performance research and profiling across the stack, Contribute to upstream open-source virtualization projects, Architect security boundaries for multi-tenant isolation
Seniority
Staff, Technical Leadership
