Openai
Systems Software Engineer, Silicon Bringup
San Francisco, Remote. Posted 2 months ago
The role
You will work on systems software strategy and execution to bring new AI silicon from first power-on to fully integrated systems. You will define software validation for compute, memory, interconnect, and I/O subsystems and build necessary diagnostics and automation.
What you will do
- Contribute to 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 system-level interactions.
- Build diagnostics, test automation, telemetry, and regression infrastructure.
- Lead bringup from initial silicon arrival through board and system integration, docking, runtime enablement, and model execution.
- Design stress tests to characterize reliability, performance, and stability.
- Translate architecture specifications and performance models into acceptance criteria and coverage goals.
- Debug complex hardware-software failures and coordinate fixes across teams.
- Validate that integrated systems deliver expected functionality and model performance.
Required qualifications
- Strong systems programming experience in C, C++, Rust, Python, or comparable low-level environments.
- Experience bringing up or validating complex silicon, accelerators, servers, or other hardware-software systems.
- Understanding of computer architecture and the behavior of compute, memory, interconnect, and I/O subsystems.
- Skill at low-level debugging across firmware, drivers, operating systems, and hardware interfaces.
- Ability to create a rigorous test strategy, reason about coverage gaps, and build scalable automation and observability.
- Experience with performance characterization, stress testing, reliability testing, or production readiness.
- Ability to communicate clearly across disciplines and drive ambiguous, high-stakes technical work.
About the company
OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. The Hardware organization develops AI-native silicon and system-level solutions for advanced AI workloads.