Senior Staff Software Engineer, Linux Kernel

Job Title

Senior Staff Software Engineer, Linux Kernel

Role Summary

Owner of the Linux kernel-mode driver for an accelerator-class Fabric architecture. Work on pre-silicon bring-up, emulation, FPGA prototypes, and first-silicon enablement to ensure runtime software and kernel interfaces function on day one.

This role sits on the System Software team and collaborates closely with architecture, microarchitecture, verification, compiler, and hardware teams.

Experience Level

Senior-level. The role expects 7+ years of systems software experience with substantial Linux kernel-mode driver work.

Responsibilities

Primary responsibilities include building and validating the kernel driver, enabling platforms before and after silicon, and establishing test and debug infrastructure.

• Design, implement, and maintain the Linux kernel-mode driver: device probe, MMIO register interfaces, interrupts, command/completion queues, power management, firmware interaction, diagnostics, logging, and user-space ABI/HAL.
• Define kernel interfaces for custom accelerators: ioctl/sysfs, submission/synchronization model, and HAL exposed to runtime.
• Implement unified/shared memory model between ARM cores and the accelerator and integrate SMMU/IOMMU (stream/context config, page tables, SVAs, fault handling).
• Lead pre-silicon bring-up: build and maintain QEMU device models and board definitions to validate kernel and runtime before silicon.
• Own Linux boot path and early platform enablement across emulation, FPGA prototypes, and first silicon (firmware handoff, device tree, kernel config, early console, root filesystem).
• Lead kernel-side first-silicon bring-up: validate MMIO maps, interrupts, clocks, resets, and memory; generate bug reports and hardware feedback.
• Debug kernel and system-level failures using crash analysis, KGDB/JTAG, ftrace, perf, lockdep, KASAN, and hardware debuggers.
• Establish kernel-level test coverage: driver unit tests, emulation-based regression suites, and hardware-in-the-loop validation.

Requirements

Must-have technical skills and experience required to perform the role. Education requirements are summarized separately below.

• 7+ years systems software experience with substantial hands-on Linux kernel-mode driver development for complex devices (accelerators, GPUs, NPUs, networking, or storage).
• Deep knowledge of Linux kernel memory management: cache coherence, IOMMU/SMMU configuration, and shared/unified virtual memory between CPU and accelerators.
• Hands-on experience with QEMU, emulation, or simulation environments, including writing or extending device models and board definitions.
• Experience with pre-silicon hardware bring-up and first-silicon enablement from register maps and hardware specs.
• Designing runtime interfaces between kernel and user space: ABI/HAL design, synchronization, memory sharing, and error handling.
• Strong kernel debugging skills: crash dumps, tracing, hardware debuggers, race and memory-corruption diagnosis.
• Fluency with memory-mapped I/O: register-level programming, ordering/barrier semantics, and interrupt handling.
• Strong experience with ARM architecture (AArch64): exception levels, GIC, SMMU, cache and memory attributes.
• Solid understanding of Linux boot flow and early platform enablement (firmware, device tree, kernel init).
• Expert C and strong scripting skills; comfortable using AI-assisted development tools for code and debugging.

Nice-to-have:

• FPGA prototyping and hardware emulation platform experience (Palladium, Zebu, Veloce, or similar).
• Familiarity with dataflow or spatial compute architectures and how compilers/runtimes target them.
• Experience on first-generation silicon products or with CUDA/ROCm or other language runtime stacks.

Education Requirements

B.S. in Electrical/Computer Engineering, Computer Science, or equivalent practical experience. M.S. is a plus. The posting explicitly allows equivalent practical experience in lieu of a degree.

About the Company

Company: Efficient Computer

Headquarters: Austin, TX, USA

Developer of ultra-low-power general-purpose processors using patented technology that can consume up to 100x less energy than comparable ultra-low-power processors. Their programmable platform supports standard high-level languages and AI/ML frameworks to enable long-lived, battery-powered edge devices and energy-efficient SoCs for IoT and edge AI applications.