The posting
About the Team
We are a systems software team building the foundational software for large-scale GPU computing cluster. We work at the hardware/software boundary across the Linux kernel, accelerators, storage, firmware, and platform validation. We value rigorous engineering, clear interfaces, measurable performance and reliability, and upstream collaboration where appropriate. The team partners closely with hardware, architecture, product, validation, and production engineering groups to move new capabilities from design through dependable deployment.
About the Role
You will own substantial Linux kernel features and production issues from design through validation and deployment. This is a senior individual-contributor role for an engineer who writes and reviews low-level code, diagnoses failures across hardware and software boundaries, and delivers measurable improvements in reliability, performance, security, and maintainability. You will influence designs and help other engineers succeed, while remaining directly accountable for implementation and results.
Responsibilities
- Backport, design, implement, optimize, and maintain Linux kernel components and associated user-space interfaces for production compute platforms.
- Own complex features through requirements, design review, coding, integration, validation, rollout, and post-deployment support.
- Debug kernel crashes, hangs, race conditions, memory corruption, boot failures, performance regressions, and hardware/software interaction defects from the production environment in real cases.
- Analyze traces, logs, crash dumps, performance counters, and workload behavior to identify root causes and verify corrective action.
- Improve observability and diagnostic tooling for field issues, and develop automated unit, integration, stress, fault-injection, and regression tests;
- Partner with silicon, firmware, security, validation, platform, and production teams to enable new hardware and resolve cross-layer defects.
- Contribute patches and technical discussions upstream when upstream adoption is the appropriate long-term path; maintain downstream changes responsibly when it is not.
- Review designs and code, document operational constraints, and share practical kernel-debugging knowledge with the team and partner team.
Minimum qualifications
- Bachelor’s degree in Computer Science, Computer Engineering, Electrical Engineering, or equivalent practical experience.
- Deep understanding of operating-system fundamentals, including concurrency, memory management, scheduling, interrupts, synchronization, and device I/O.
- 3+ years of professional experience developing systems software in C, with working knowledge of C++ and scripting languages used for automation and diagnostics.
- Hands-on Linux kernel development or debugging experience in one or more areas such as device drivers, platform enablement, virtualization, networking, security, power management, or core kernel infrastructure.
- Demonstrated ownership of production-quality software, including testing, code review, incident diagnosis, and sustained maintenance.
- Clear written and verbal communication across hardware and software disciplines.
Preferred qualifications
- Experience contributing to the upstream Linux kernel or another substantial open-source systems project.
- Familiarity with kernel tracing and debugging tools such as ftrace, perf, eBPF, crash, kdump, lockdep, KASAN, or equivalent facilities.
- Experience enabling new silicon or server platforms, including firmware interfaces, PCIe devices, interrupt routing, IOMMU, or power and thermal behavior.
- Evidence of improving a production system’s availability, latency, throughput, security, or recovery time through hands-on engineering.
