Kernel Driver Software Engineer

About the Company

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. We are a fully in-person team in San Jose (Santana Row) focused on redefining the infrastructure layer for the fastest growing industry in history.

Responsibilities

• Design, develop, and maintain kernel-mode drivers ensuring high reliability and optimal performance
• Analyze and optimize driver performance for demanding AI workloads
• 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 strategies including kernel memory mapping, page tables, and IOMMU configuration
• Build kernel drivers designed to support security across host processes and device attestation
• Diagnose and resolve complex driver-related issues using tools like ftrace and dmesg
• Design and implement synchronization mechanisms for concurrent access to multiple accelerators
• Develop and execute comprehensive test plans for manufacturing and production environments

Requirements

• Proficiency in C/C++
• Strong understanding of kernel-mode driver development and debugging
• Deep understanding of Linux operating system internals
• 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 technologies (SR-IOV, VFIO)
• Experience with version control systems like Git
• Experience with debugging tools such as gdb or kgdb

Preferred Qualifications

• Experience developing kernel-mode drivers for GPUs or other accelerator devices
• Experience with CUDA, OpenCL, or other GPU programming models
• Experience with ML frameworks like TensorFlow or PyTorch
• Experience with performance profiling tools like perf or VTune
• Knowledge of Rust
• Experience with data center orchestration like Kubernetes or Docker
• Experience with CI/CD pipelines