Supercomputing Engineer

About Etched

Etched is building the world’s first AI inference system purpose-built for transformers - delivering over 10x higher performance and dramatically lower cost and latency than a B200. With Etched ASICs, you can build products that would be impossible with GPUs, like real-time video generation models and extremely deep & parallel chain-of-thought reasoning agents. Backed by hundreds of millions from top-tier investors and staffed by leading engineers, Etched is redefining the infrastructure layer for the fastest growing industry in history.

Job Summary

Etched is building at-scale AI systems that will unlock faster, more efficient inference for billions of people, and the Supercomputing team is critical in enabling this mission. We are seeking a highly skilled and motivated Engineer to join our Supercomputing team to help build the foundational software that powers our cluster-scale AI compute deployments. This role on the core team involves the development, integration, and debugging of critical system components, including on control-plane software, system bring-up, telemetry, orchestration primitives, and performance tuning at the hardware–software boundary.

Key Responsibilities

• Architect and implement low-level control-plane software responsible for system bring-up, configuration, 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 and behavior
  

Must-Have Skills and Experience

• 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
  

Nice-to-Have Skills and Experience

• 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, ftrace, or custom instrumentation

• Experience taking complex systems from early bring-up through stable operation

• Background in HPC, AI infrastructure, or large-scale compute systems

• Experience designing system test harnesses and failure-injection frameworks

• Familiarity with Kubernetes or cluster orchestration at the node or control-plane level

Benefits

• Medical, dental, and vision packages with generous premium coverage

  • $500 per month credit for waiving medical benefits

• Housing subsidy of $2k per month for those living within walking distance of the office

• Relocation support for those moving to San Jose (Santana Row)

• Various wellness benefits covering fitness, mental health, and more

• Daily lunch + dinner in our office

How we’re different

Etched believes in the Bitter Lesson. We think most of the progress in the AI field has come from using more FLOPs to train and run models, and the best way to get more FLOPs is to build model-specific hardware. Larger and larger training runs encourage companies to consolidate around fewer model architectures, which creates a market for single-model ASICs.

We are a fully in-person team in San Jose (Santana Row), and greatly value engineering skills. We do not have boundaries between engineering and research, and we expect all of our technical staff to contribute to both as needed.