About the job
You will set the technical direction for Crusoe's Linux kernel team, owning the roadmap and architecting critical development projects. This role requires a balance of high-level architectural design and hands-on kernel coding. You will tackle the most complex kernel problems while mentoring and growing the engineers around you to deliver production-ready infrastructure at scale.
Responsibilities
- Design and implement advanced virtualization technologies tailored for GPU-accelerated AI and HPC workloads, optimizing the stack for low latency and high scalability across hypervisors and device emulation.
- Develop and maintain upstream-first kernel code and device drivers, optimizing memory management, scheduling, and I/O subsystems to support hardware accelerators and high-throughput compute use cases.
- Perform deep-dive root-cause analysis of issues across the OS and hardware layers, lead triage and backporting for kernel CVEs, and build automated tooling for vulnerability analysis.
- Lead and grow a high-performing systems team by driving engineering excellence through technical mentorship, comprehensive code reviews, and alignment with product and hardware teams.
Qualifications
Minimum
- 10+ years of experience in systems software engineering with at least 3 years in a technical leadership role managing low-level systems or infrastructure teams.
- Expert-level knowledge of Linux kernel internals (memory management, scheduler, I/O) and virtualization technologies (KVM, Xen, or QEMU).
- Strong C programming skills and fluency with the kernel development workflow, including patch submission and debugging security vulnerabilities.
- Proficiency in modern systems programming (Go, Rust, or Python) and familiarity with CI/CD and deployment automation tooling.
Preferred
- Familiarity with accelerators (GPUs, TPUs) and related technologies like CUDA or ROCm.
- Experience with high-performance networking (e.g., InfiniBand, RoCE) and tuning virtualization stacks for HPC workloads.