Senior Compute Engineer: AI Infra, Kernel & Virtualization

crusoe; Sunnyvale (CA); On-site; USD 170,000 - 205,000; Full time

Benefits offered by this job

Health insurance

RSUs

401(k) match

Parental leave

Life insurance

Disability insurance

Tuition reimbursement

Commuter benefits

Cell phone reimbursement

PTO

Job summary

Crusoe Energy Systems is seeking a Compute SRE/Production Engineer to strengthen the AI-first cloud infra that powers modern workloads. You will help deploy and optimize bare-metal and virtualized compute platforms, focusing on performance, security, and scale for AI and HPC tasks.

You will develop automation and observability tools, support virtualization stacks (KVM/QEMU/Xen/VMware), and work with kernel/hardware teams to resolve performance issues and improve guest reliability.

Qualifications

• 5+ years in Compute SRE, Linux system engineering, or compute infra roles.
• Strong experience with Linux kernel internals and scheduler.
• Hands-on with virtualization architectures (KVM/QEMU/Xen/VMware).
• Familiarity with SmartNICs/DPUs and kernel bypass techniques.
• Proficient in Go, C or Rust and in IaC/CI/CD for bare-metal or cloud.

Responsibilities

• Develop automation and observability tools for Crusoe's compute infra.
• Support and scale the virtualization stack and kernel-level performance.
• Collaborate with Linux kernel and hardware teams to resolve bottlenecks.
• Tune kernel subsystems and optimize AI/HPC workloads across CPU/GPU/DPUs.

Skills

Linux kernel internals

Hypervisors

Go / C / Rust

Kernel debugging

Infrastructure as Code

Scheduling / resource mgmt

High-throughput networking

SRE / Linux system engineering

Tools

KVM

QEMU

Xen

VMware

Job description

Crusoe Energy Systems is seeking a Compute SRE/Production Engineer to strengthen the AI-first cloud infra that powers modern workloads. You will help deploy and optimize bare-metal and virtualized compute platforms, focusing on performance, security, and scale for AI and HPC tasks.

You will develop automation and observability tools, support virtualization stacks (KVM/QEMU/Xen/VMware), and work with kernel/hardware teams to resolve performance issues and improve guest reliability.