Head of Supercomputing

Job Title

Head of Supercomputing

Role Summary

The Head of Supercomputing will define and lead the architecture, software stack, and operational model for Etched’s cluster-scale AI inference systems.

This role owns end-to-end system software and control-plane strategy — orchestration, telemetry, provisioning, networking, and fleet reliability — from first silicon through production deployment, and builds a high-performance engineering organization to deliver deployable, reliable supercomputers.

Experience Level

Senior — 15+ years in system software, infrastructure, or large-scale compute systems; includes 5+ years leading engineering teams.

Responsibilities

Lead technical direction, team building, and delivery for cluster-scale AI compute systems.

• Define and drive the technical vision and roadmap for the Supercomputing software stack from node bring-up to multi-rack clusters.
• Build, scale, and lead the Supercomputing organization; directly manage and develop 15+ engineers.
• Architect and own low-level control-plane software for bring-up, provisioning, networking, configuration, and fleet management.
• Define orchestration primitives for devices, nodes, racks, and full cluster deployments.
• Oversee development of system services that interface with firmware, drivers, kernel subsystems, and runtime layers.
• Establish system telemetry, observability infrastructure, reliability targets, operational metrics, and release processes for production deployments.
• Integrate diagnostics and system software into manufacturing and test environments.
• Collaborate cross-functionally with ASIC, hardware, kernel, runtime, and infrastructure teams.
• Act as a senior technical voice shaping company-wide infrastructure decisions.

Requirements

Must-have technical and leadership qualifications for this role.

• 15+ years in system software, infrastructure, or large-scale compute systems, with 5+ years managing engineering teams.
• Deep understanding of hardware/software interfaces: PCIe, RDMA, memory hierarchies, interrupts, and device drivers.
• Experience building or operating cluster-scale systems (HPC, AI infrastructure, hyperscale compute, or custom accelerators).
• Proven record of delivering complex systems from early bring-up through stable production releases.
• Strong debugging skills across hardware–software interactions and experience with orchestration, provisioning, telemetry, and fleet reliability.
• Excellent leadership, communication, hiring, mentoring, and cross-functional collaboration skills.

Education Requirements

Not specified.

About the Company

Company: Etched

Headquarters: San Jose, CA, United States

Etched develops purpose-built AI inference ASICs and systems optimized for transformer models, aiming to deliver significantly higher performance, lower cost, and lower latency than GPUs. The company focuses on enabling applications like real-time video generation and advanced reasoning agents, and is backed by leading investors and engineers.