9 months ago
Remote, EMEA or Amsterdam, NetherlandsSenior
Responsibilities
- Ensure the reliability, availability, and performance of compute nodes running virtual machines.
- Analyze and debug Linux systems across user space and kernel space.
- Troubleshoot production issues involving CPU, memory, NUMA, cgroups, and scheduling.
- Work hands-on with virtualization and containerization using QEMU/KVM and Linux-native technologies.
- Design and evolve observability capabilities including metrics, logs, traces, alerts, SLIs, and SLOs.
- Lead incident response, root-cause analysis, and postmortems while driving long-term reliability improvements.
- Collaborate with platform, kernel/hypervisor, GPU, and infrastructure teams to improve system design and operability.
Requirements
- Deep expertise in Linux user space, kernel space, kernel subsystems, system boundaries, and system constraints.
- Hands-on experience with QEMU/KVM and understanding of VM lifecycles, performance characteristics, and failure modes.
- Practical experience with containers, namespaces, and cgroups, including resource isolation and control.
- Strong ability to analyze complex system failures using a structured, hypothesis-driven approach.
- Understanding of SRE principles, system design and operations, and experience building and operating observability stacks.
- Experience with Kubernetes internals or node-level components is preferred.
- Experience with perf, eBPF, ftrace, strace, or kernel crash dumps is preferred.
- Familiarity with large-scale compute or bare-metal platforms is preferred.
- Open-source infrastructure or system software contributions are preferred.
- Experience debugging hardware and driver-level issues involving GPUs, NVLink, or InfiniBand is preferred.
Benefits
- Competitive salary and comprehensive benefits package.
- Professional growth opportunities within Nebius.
- Flexible working arrangements.
- Dynamic and collaborative work environment.
Tech Stack
Categories
Site Reliability
About Nebius
Nebius builds a full-stack AI cloud offering GPU compute, storage, and tools for training and deploying ML models for startups, enterprises, and research labs. It sells consumption-based cloud infrastructure (IaaS/PaaS) and managed services tailored to generative AI workloads, including large-scale model training and inference. The company is headquartered in Amsterdam and operates as an independent provider.