Senior Kernel Engineer — Kubernetes & Cloud AI

CoreWeave; Bellevue (WA); On-site; USD 182,000 - 242,000; Full time

Benefits offered by this job

Medical, dental, vision insurance

401(k) with employer match

Flexible PTO

Tuition Reimbursement

ESPP

Job summary

CoreWeave is the essential cloud platform for AI, enabling researchers and enterprises to build and scale AI workloads with confidence. The Senior Software Engineer on the Systems Engineering team dives into the Linux kernel and host stack to diagnose complex failures and craft robust fixes that survive fleet-scale usage.

You will collaborate across hardware, platform, HPC, and product teams, tracing issues from kernel internals to container runtimes and upstreaming patches where applicable.

Qualifications

• 5+ years of professional experience in Linux kernel engineering, systems-level development, or a closely adjacent discipline.
• Deep understanding of kernel internals — memory management, process/thread scheduling, cgroups, namespaces, and the networking or storage stack.
• Hands-on experience with cgroups (v1 and/or v2) and namespaces, and how they underpin container isolation and resource limits.
• Experience debugging kernel crashes, panics, hangs, and dumps using tools like crash, gdb, or kdump.
• Strong C programming skills, with the ability to write maintainable, upstream-quality code.
• Working knowledge of the container and Kubernetes stack — containerd, runc, the kubelet, and the CRI — and how kernel behavior shows up at that layer.
• Skilled at cross-domain debugging: identifying whether a root cause lies in the kernel, the container runtime, or the orchestration layer above it.

Responsibilities

• Debug and fix complex issues that span the kernel/Kubernetes boundary — pods stuck or evicted for unclear reasons, cgroup memory/CPU accounting that doesn't add up, namespace or mount issues that only manifest under real workloads at scale.
• Go deep into cgroups (v1 and v2), namespaces, the OOM killer, and the CPU scheduler (CFS) to explain and fix behavior that looks like a Kubernetes bug but is actually a kernel one — and the reverse.
• Debug kernel crashes, panics, oopses, and hangs using tools like crash, gdb, and kdump; identify root cause and drive it to a fix.
• Work across the container runtime stack (containerd, runc, the kubelet, the CRI) to understand how kernel behavior surfaces as pod- and container-level symptoms.
• Develop and, where applicable, upstream Linux kernel patches — to the mainline kernel, container runtimes, or Kubernetes itself.
• Build diagnostics and tooling for kernel- and cgroup-level observability, so the next issue like this is faster to find.
• Partner with hardware, platform, HPC, and Fleet teams to ensure kernel and container-runtime readiness for production workloads, and provide kernel-level expertise during incident response and root-cause investigations.

Skills

Linux kernel

Systems-level development

Kernel internals

C programming

Container/Kubernetes stack

Tools

crash

gdb

kdump

containerd

runc

kubelet

CRI

Job description

CoreWeave is the essential cloud platform for AI, enabling researchers and enterprises to build and scale AI workloads with confidence. The Senior Software Engineer on the Systems Engineering team dives into the Linux kernel and host stack to diagnose complex failures and craft robust fixes that survive fleet-scale usage.

You will collaborate across hardware, platform, HPC, and product teams, tracing issues from kernel internals to container runtimes and upstreaming patches where applicable.