About the RoleYou will work on the systems software strategy and execution that brings new AI silicon from first power-on to a fully integrated system running production-representative models at expected functionality and performance. You will define how software exercises and validates compute, memory, interconnect, and I/O subsystems, then build the diagnostics, automation, and observability needed to find issues quickly.
This role sits at the center of silicon, firmware, platform, systems, and workload teams. You will turn hardware specifications and performance targets into an end-to-end bringup plan, drive cross-functional debug, and establish the stress and regression infrastructure that makes each new platform reliable across operating environments.
In this role, you will:- Contribute to the end-to-end software bringup and validation strategy for new silicon and first-party systems.
- Define software-driven test coverage across compute, memory, interconnect, I/O, and their system-level interactions.
- Build diagnostics, test automation, telemetry, and regression infrastructure that accelerate first-silicon learning and issue isolation.
- Lead bringup from initial silicon arrival through board and system integration, docking, runtime enablement, and model execution.
- Design stress tests that characterize reliability, performance, and stability across workloads and operating conditions.
- Translate architecture specifications and performance models into measurable acceptance criteria, coverage goals, and pass/fail signals.
- Debug complex hardware-software failures, drive root-cause analysis, and coordinate fixes across silicon, firmware, electrical, platform, and workload teams.
- Validate that integrated systems deliver expected functionality and model performance, and turn bringup learnings into reusable infrastructure for future generations.
You might thrive in this role if you:- Have strong systems programming experience in C, C++, Rust, Python, or comparable low-level environments.
- Have brought up or validated complex silicon, accelerators, servers, or other hardware-software systems.
- Understand computer architecture and the behavior of compute, memory, interconnect, and I/O subsystems.
- Are skilled at low-level debugging across firmware, drivers, operating systems, and hardware interfaces.
- Can create a rigorous test strategy, reason about coverage gaps, and build scalable automation and observability.
- Have experience with performance characterization, stress testing, reliability testing, or production readiness.
- Communicate clearly across disciplines and can drive ambiguous, high-stakes technical work from plan through closure.
- Care deeply about building durable tools and processes that make subsequent bringup cycles faster and more predictable.
To comply with U.S. export control laws and regulations, candidates for this role may need to meet certain legal status requirements as provided in those laws and regulations.
