**Role & seniority: ** GPU Server Engineer (technical, hands-on); ~1–5 years experience expected

**Stack/tools: **

Hardware/firmware/platform: silicon, GPU power management features, BIOS, system firmware, OS integration
Debug/validation: emulation, post-silicon validation, lab instrumentation (e.g., oscilloscope, logic analyzer, protocol analyzer)
Software/scripting: C/C++, Python, Perl (or similar)
OS/driver context: Linux and/or Windows Server, GPU drivers/firmware usage; PCIe, memory/bus logic knowledge
Top 3 responsibilities:
1. Coordinate with power/architecture, silicon, firmware, and platform teams to evaluate and enable server GPU power management features (pre-silicon → post-silicon).
2. Create and execute feature enablement + validation test plans (emulation and post-silicon across server GPU products).
3. Build post-silicon validation infrastructure and lead debug/root-cause efforts; optimize power management for performance targets.
Must-have skills:
- Computer hardware + software architecture understanding (CPU/APU/GPU, x86, PCIe, memory, buses; drivers, BIOS/firmware, OS usage)
- Knowledge of power management features including Vmin voltage bounding box, power/performance behavior
- Silicon bring-up/post-silicon validation + debugging at GPU and system level
- Validation methodology/test development

Full Description

GPU Server Engineer

Technical, hands-on engineer responsible for Datacenter GPU power management feature validation, feature enablement at the silicon GPU level up through BIOS/system firmware/OS levels, and feature optimization towards power and performance

Interface silicon, power architect, firmware and platform team to close power management feature evaluation in pre-silicon phase
Develop and execute feature enablement and validation test plans for power management features during emulation and post silicon phase across all Server GPU products
Develop post-silicon validation infrastructure (software, hardware, automation environment, and lab setup)
Drive post-silicon debug efforts to identify root cause and resolution of newest Server GPU
Drive post silicon power management feature optimization toward performance target
Work with cross-functional teams internally and externally to improve post-silicon validation test strategy, methodology, and process
Leading collaborative technical discussions to drive resolution on technical issues and roll out technical initiatives
Be able to work in a high demand, fast paced environment with lots of real-time problem solving and critical thinking

Knowledge of computer hardware architecture (CPU/APU, GPU, x86, pcie, memory, bus logic) and software architecture (driver, bios, firmware usage)
Knowledge of power management features, Vmin voltage bounding box, power and performance
Understanding of modern x86 microprocessor architecture and Server GPU platform architecture is highly desired
Experience developing validation methodologies and infrastructure
Test plan and test development experience
Participated in silicon bring up and debug, support to internal engineering teams
Able to execute and drive success of programs with multiple projects on the go
Debug skills at both GPU and system level
Familiarity with programming / scripting language (C/C++, Python, Perl, ...)
Working knowledge of Server OSes (Linux, Windows Server)
Must be a self-starting team player with excellent communication skills who can work with minimal guidance
Forward thinker that drives improvement to development process, code architecture and fosters a spirit of innovation and continuous improvement
Strong verbal and written English communication skills
Working knowledge of lab equipment such as oscilloscopes, logic analyzers and protocol analyzers
Self-organizing and the ability multitask based on priorities

Bachelor’s degree or higher in Electrical/Computer Engineering or Electronics / Computer Science related with a minimum 1-5 years of experience in SoC validation and debug.