Senior Systems Software Engineer, GPU Compute

Kurz zusammengefasst

Nebius is seeking a Senior Systems Software Engineer, GPU Compute to build low‑level runtime and driver components that power high‑performance GPU workloads on its multi‑cloud platform. You will work closely with hardware partners, kernel teams and cloud‑infrastructure engineers, mentor junior staff, lead technical reviews and help shape the roadmap for next‑generation compute services. Day‑to‑day you will design and optimise runtime code, develop Linux kernel modules, profile performance, manage concurrency and integrate with container orchestration and cloud‑native CI/CD pipelines. The role is based in Amsterdam, London or Poland, within a fast‑growing European cloud provider and a world‑class research and engineering community. What the role asks for: - Minimum 7 years systems programming (C/C++) experience - Deep knowledge of GPU architectures: CUDA, ROCm, Vulkan - Proven Linux kernel development expertise - Experience with performance profiling and concurrency - Experience with Kubernetes container orchestration - Experience with cloud‑native CI/CD pipelines - Ability to mentor junior engineers - Nice‑to‑have: experience shaping compute service roadmaps