System Software Engineer — Node & Cluster Management (AI)

Location: Bay Area, California, United States

Salary: $200,000–$350,000 per year

Company

Early-stage AI hardware company building high-performance accelerator systems for large-scale AI workloads.

What you will do

• Design and build node-level management planes for AI accelerator systems.
• Expose health, inventory, telemetry, diagnostics, and control through HTTP/REST APIs.
• Develop cluster management, failover, recovery, availability, and fleet-wide health aggregation.
• Build Linux management and telemetry daemons, CLI tools, provisioning workflows, and test automation.
• Integrate host-side software with BMC and out-of-band interfaces, device software, and firmware.
• Debug issues across APIs, userspace daemons, kernel drivers, firmware, and hardware.

Requirements

• 8+ years of experience in systems, infrastructure, platform, or hardware-management software.
• Strong Linux systems programming experience and experience developing low-level userspace software and Linux daemons.
• Strong C skills plus experience with Go, Rust, C++, and/or Python.
• Experience building REST APIs and CLI tooling for hardware or infrastructure systems.
• Understanding of device drivers, PCIe devices, hardware telemetry, firmware interfaces, and BMC-managed subsystems.
• Ability to collaborate with firmware and hardware engineers in an early-stage environment with evolving specifications.

Nice to have

• Experience with Redfish, OpenBMC, IPMI, or gNMI.
• GPU, accelerator, HPC, datacenter fleet, or large-scale Linux infrastructure experience.
• Experience with secure boot, device attestation, firmware recovery, hardware bring-up, or lab infrastructure.

Culture & Benefits

• Hands-on work in an early-stage AI hardware environment.
• Direct collaboration across software, firmware, and hardware engineering.
• Opportunity to define management interfaces for a new AI platform from individual servers through full-scale clusters.