About the Role
We’re looking for an experienced systems software engineer to help define and build the host software stack for our custom next-generation AI systems. You will work close to the hardware on performance-critical software, including Linux kernel drivers, high-throughput I/O paths, and system-scale networking and RDMA. This role spans architecture, implementation, platform bring-up, debugging, and performance optimization. You will work across hardware and software boundaries to make new systems usable end to end, from low-level device interfaces through userspace tooling and production validation.
In this role you will:
- Design, implement, and debug host-side systems software for AI infrastructure, including Linux kernel drivers and supporting userspace components.
- Build and optimize software paths for high-throughput, low-latency communication, including RDMA and related networking functionality.
- Develop software around PCIe, DMA, NICs, accelerators, memory movement, and device interaction.
- Bring up new hardware platforms and diagnose complex issues across kernel, firmware, networking, and hardware boundaries.
- Build tooling for integration, testing, diagnostics, observability, qualification, and performance characterization.
- Collaborate with hardware, networking, and platform teams to define interfaces and integrate new capabilities.
- Work with external vendors where needed to integrate technologies and drive issues to resolution.
- Contribute across the systems software stack as the platform and team evolve.
- Help shape the technical direction and engineering practices for a growing systems software stack.
You might thrive in this role if you have:
- Experience building low-level or performance-critical systems software.
- Strong programming skills in C or C++, with proficiency using Python and Linux tooling for automation and debugging.
- Strong Linux systems fundamentals and the ability to debug across hardware and software boundaries.
- Hands-on experience in at least one relevant area, such as Linux kernel drivers, kernel networking, RDMA, PCIe, DMA, NIC software, accelerator software, or high-performance I/O.
- Experience owning complex software projects from design through implementation, bring-up, and validation.
- Ability to thrive in ambiguity, work across subsystem boundaries, and build systems from scratch.
- Strong cross-functional communication skills.
Preferred Qualifications
- Experience developing Linux kernel drivers or other OS-level performance-critical components.
- Familiarity with RDMA or RoCE, ibverbs, kernel networking, or congestion-control concepts such as ECN and DCQCN.
- Experience with PCIe, DMA, peer-to-peer communication, SR-IOV, IOMMU, dma-buf, or related accelerator and I/O subsystems.
- Experience bringing up accelerators, NICs, SoCs, or custom hardware platforms.
- Experience profiling and optimizing high-throughput, low-latency systems.
- Familiarity with Rust or experience using Rust for systems programming.