GPU Runtime Systems Engineer (Kubernetes & Security)

Coreweave; New York (NY); On-site; USD 182,000 - 242,000; Full time

Job summary

CoreWeave is seeking a GPU & Runtime Systems Engineer to design, build, and evolve secure sandboxed runtime environments for Kubernetes workloads. You will integrate container runtimes, lightweight VMs, and virtualization technologies to support GPU-accelerated workloads in multi-tenant environments.

Day-to-day you’ll develop GPU-aware sandboxing and scheduling strategies, optimize containerization and I/O performance for latency-sensitive workloads, and influence architectural decisions

Qualifications

• 3+ years of experience in systems, platform, infrastructure, or production engineering at scale.
• Strong hands-on experience with Kubernetes, container orchestration, and cloud-native architectures.

Responsibilities

• Design, build, and evolve secure sandboxed runtime environments for Kubernetes workloads.
• Develop GPU-aware sandboxing and scheduling strategies for multi-tenant workloads.
• Optimize container, VM, and I/O performance for latency-sensitive workloads.
• Conduct profiling, benchmarking, and performance tuning for runtime, virtualization, and GPU stacks.
• Contribute to architectural decisions across Linux internals, container runtimes, virtualization layers, and GPU drivers.
• Collaborate with security, platform, and infrastructure teams to define and implement runtime isolation and performance standards.

Skills

Kubernetes

Go

C/C++

Rust

Linux internals

Performance profiling

GPU workloads

Tools

Kata Containers

gVisor

KubeVirt

QEMU

Job description

CoreWeave is seeking a GPU & Runtime Systems Engineer to design, build, and evolve secure sandboxed runtime environments for Kubernetes workloads. You will integrate container runtimes, lightweight VMs, and virtualization technologies to support GPU-accelerated workloads in multi-tenant environments.

Day-to-day you’ll develop GPU-aware sandboxing and scheduling strategies, optimize containerization and I/O performance for latency-sensitive workloads, and influence architectural decisions