23 hours ago
Taipei, TaiwanMid Level
Responsibilities
- Own the quality gate determining when new firmware and software can ship to on-premises AI data centers.
- Build automated qualification pipelines that install, test, and validate releases on real TPU clusters.
- Develop test infrastructure across TPU trays, server firmware including BMC, BIOS, and NIC, optical circuit switches, networking, power, and storage.
- Run ML workloads and benchmarks to detect performance regressions before customer release.
- Create tooling to track test coverage and determine what requires re-testing after firmware changes.
- Partner with firmware, software, and release teams to diagnose and resolve complex bugs across the stack.
Requirements
- Bachelor’s degree or equivalent practical experience.
- At least 1 year of software development experience in one or more programming languages, such as Python or Go.
- At least 1 year of experience with data structures and algorithms.
- Preferred: master’s degree in computer science or a related technical field.
- Preferred: experience building test automation, CI, or qualification frameworks for hardware or firmware.
- Preferred: experience running ML benchmarks or AI workloads such as MaxText or vLLM to validate accelerator performance.
- Preferred: familiarity with cloud or data center compute, AI infrastructure software, Linux, server firmware, and ML accelerators such as TPU, GPU, and NPU.
- Preferred: experience working cross-functionally with engineers, product managers, and technical program managers.
About Google
Google builds consumer and enterprise software and services including Search, Android, YouTube, Chrome, Maps, Gmail, and Google Cloud. Its business model centers on digital advertising and paid cloud, software, and hardware offerings (e.g., Pixel and Nest) for consumers, developers, and organizations. Founded in 1998 and headquartered in Mountain View, California, Google operates globally as a subsidiary of Alphabet Inc.
