Supercomputing 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. Our first products are heavily focused on inference.

Responsibilities

• Architect and implement low-level control-plane software for system bring-up and management of cluster-scale AI compute deployments
• Build system services that interact directly with hardware, firmware, and the operating system
• Develop telemetry, logging, and tracing infrastructure for diagnosing failures and driving performance improvements
• Implement orchestration primitives for managing devices, nodes, and racks
• Profile and tune performance across PCIe, memory, networking, kernel, and runtime layers
• Collaborate closely with hardware, firmware, kernel, and runtime teams to co-design system interfaces

Requirements

• Strong proficiency in C/C++ or Rust for low-level systems programming
• Deep understanding of Linux internals, kernel/user-space boundaries, and system-level debugging
• Experience working close to hardware (drivers, DMA, interrupts, memory management, or device control paths)
• Strong debugging skills using logs, tracing, and low-level observability tools
• Strong communication skills and comfort collaborating across hardware and software teams

Preferred Qualifications

• Experience with data center orchestration technologies such as Kubernetes and Docker
• Experience with kernel development, device drivers, or firmware-adjacent software
• Familiarity with PCIe, NUMA, networking, or high-speed interconnects
• Experience with tracing and profiling tools such as perf, eBPF, or ftrace
• Background in HPC, AI infrastructure, or large-scale compute systems
• Experience designing system test harnesses and failure-injection frameworks