Compute Infra Engineer — Linux Kernel and Virtualization

ProducePay; Sunnyvale (CA); On-site; USD 209,000 - 253,000; Full time

Benefits offered by this job

Restricted Stock Units

Health insurance

Paid time off

401(k) plan

Tuition reimbursement

Commuter benefits

Cell phone stipend

Volunteer time off

Job summary

Crusoe Energy Systems is seeking seasoned Compute SREs to optimize and scale our AI-first compute infrastructure. You will work on virtualization, kernel-level performance, and hardware offloads to support AI and HPC workloads across CPU, GPU, and DPU/NIC resources.

You will develop automation, observability, and kernel-tuning strategies, collaborating with kernel, hardware, and platform teams to improve guest VM reliability and workload isolation.

Qualifications

• 8+ years in Compute SRE, Linux system engineering, or similar.
• Deep knowledge of Linux kernel subsystems and schedulers.
• Strong debugging and performance optimization skills.

Responsibilities

• Develop automation and observability tools for compute infra.
• Support and scale virtualization stack (KVM, QEMU, others).
• Identify and resolve performance bottlenecks and driver issues.
• Tune kernel subsystems for AI/HPC workloads.
• Analyze kernel crashes and contribute to reliability improvements.
• Collaborate on emerging compute hardware support.

Skills

Linux kernel internals

KVM

QEMU

VMware

Go

C

Rust

Infrastructure as Code

CI/CD

High-throughput networking

Tools

KVM

Xen

QEMU

VMware

Job description

Crusoe Energy Systems is seeking seasoned Compute SREs to optimize and scale our AI-first compute infrastructure. You will work on virtualization, kernel-level performance, and hardware offloads to support AI and HPC workloads across CPU, GPU, and DPU/NIC resources.

You will develop automation, observability, and kernel-tuning strategies, collaborating with kernel, hardware, and platform teams to improve guest VM reliability and workload isolation.