Kernel Driver Software Engineer
Etched · San Jose
About this role
## About Etched Etched is building hardware for frontier intelligence. We co-design chips, racks, software, and manufacturing to deliver best-in-class throughput and latency across both prefill and decode workloads. Our first products are heavily focused on inference—backed by hundreds of millions from top-tier investors and staffed by leading engineers. ## Key Responsibilities - Design, develop, and maintain **kernel-mode drivers** with high reliability, informative debug, and optimal performance. - Analyze and optimize driver performance for demanding **AI workloads**, minimizing latency and maximizing throughput. - Collaborate closely with **hardware engineers** throughout the ASIC design process. - Implement driver support for **device virtualization** technologies, including **SR-IOV**, **VFIO**, and **para-virtualization**. - Implement efficient **memory management** (kernel memory mapping, page tables configuration, NUMA awareness, and IOMMU configuration). - Build kernel drivers with security in mind across host processes, physical memory spaces, and device attestation. - Diagnose and resolve complex driver issues using kernel debugging tools and techniques (e.g., **ftrace**, **dmesg**). - Design and implement **synchronization** mechanisms for concurrent access to multiple accelerators. - Develop and execute comprehensive **test plans** to validate functionality, stability, and performance in manufacturing and production. - Collaborate with software and hardware teams to resolve complex system-level issues. ## Representative Projects - Develop and optimize kernel-mode drivers for new ML accelerators. - Optimize memory management (kernel memory mapping and **IOMMU**) for high-bandwidth transfers. - Debug and resolve driver issues impacting ML workload performance. - Build performance benchmarks and profiling tools. - Integrate support for advanced features like hardware virtualization and security (e.g., **SR-IOV**, **VFIO**). - Optimize **PCIe** communication between host and devices (using PCIe analyzers). - Implement and debug **power management** for PCIe devices. - Integrate ML accelerators into **containerized and virtualized** environments. - Implement and optimize **para-virtualization** techniques. - Configure and optimize **page tables** for efficient accelerator memory access. - Participate in hardware-software co-design reviews to improve performance and power efficiency. ## You may be a good fit if you have - Proficiency in **C/C++**. - Strong understanding of **kernel-mode driver development and debugging**. - Deep understanding of **operating system internals** (Linux preferred). - Experience with **hardware/software interfacing** and device drivers. - Experience with **memory management** and **synchronization** in kernel environments. - Strong understanding of **PCIe** and other hardware interfaces. - Experience with **device virtualization** (SR-IOV, VFIO). - Strong understanding of kernel memory mapping, page tables, and **IOMMU**. - Familiarity with hardware-software co-design principles. - Proven ability to analyze complex technical problems and deliver effective solutions. - Excellent communication and collaboration. - Experience with **version control** (e.g., Git). - Experience with debugging tools (e.g., **gdb**, **kgdb**). ## Nice-to-have - Experience developing/debugging kernel-mode drivers for GPU/accelerator devices. - Strong understanding of hardware/software interactions. - Experience optimizin
Listing freshness
CronJobs last confirmed this listing 1h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.