Principal GPU​/CPU Systems Engineer

Job Description

Required Qualifications

• 10 or more years of experience in hardware design, system engineering, and platform bring-up.

• Hands-on experience with market-leading GPUs or AI platforms spanning development, bring-up, test, and characterization.

• Strong knowledge of AI/GPU and or AI/CPU platform architectures and capabilities.

• Experience evaluating system architectures, platform definitions, and implementation paths.

• Ability to balance hardware performance, power, cost, regulatory, and cross-functional requirements.

• Experience with modern server platforms across x86 and ARM architectures.

• Hardware development experience at the system, board, and FPGA levels.

• Proficiency reviewing hierarchical schematics, advanced multilayer board layouts, and end-to-end interconnects.

• Strong understanding of firmware and system diagnostics using BMC firmware, UEFI or BIOS, and Linux tools.

• Experience scripting and customizing diagnostics, validation, and test workflows.

• Experience with GPU supplier test code and open-source AI test and characterization tools.

• Experience with system integration, validation, and performance characterization.

• Strong understanding of high-speed buses and interconnects used in modern AI and compute platforms.

• Demonstrated ability to debug and root-cause complex hardware and software issues.

• Ability to document design intent and technical specifications clearly.

• Strong communication skills with the ability to explain complex technical topics across engineering teams and executive audiences.

• Proven ability to provide cross-functional technical leadership and collaborate effectively with internal teams and external partners.

Preferred Skills

• Experience using hardware debuggers.

• Experience with PCIe, DDR, Ethernet, USB, SPI, and related interfaces.

• Experience with platform-level security technologies.

• Experience with power circuit design and signal integrity.

Responsibilities

• Participate in platform definition, architecture evaluation, and analysis for existing and next-generation Cloud AI platforms.

• Evaluate system architectures, proposed implementations, and scaling and optimization strategies.

• Review and assess third-party merchant silicon used for AI accelerator modules and GPU/CPU platforms.

• Balance hardware performance priorities against power, cost, regulatory, and cross-functional requirements.

• Drive definition, development, integration, debug, characterization, and tuning of AI hardware platforms.

• Provide platform development oversight for internal teams and third-party partners.

• Work with in-house engineering experts on design reviews, schematics, board layout, and implementation decisions.

• Document and specify design intent and technical details in collaboration with engineering teams.

• Guide and support system integration, system test, qualification, and characterization.

• Define and oversee system validation plans, diagnostics features, and test strategies.

• Develop and expand system characterization and performance testing capabilities.

• Utilize supplier-provided and approved open-source AI platform qualification and test tools.

• Support definition of in-service system monitoring, error reporting, and operational health visibility.

• Collaborate with GPU and AI chip suppliers, system architects, firmware developers, and hardware engineers.

• Partner with storage, networking, compute, quality, security, cloud orchestration, and manufacturing teams.

• Support development program managers with technical assessments and planning.

• Assist manufacturing teams to ensure hardware is secure, robustly evaluated, and production-ready.

• Participate in hardware platform security evaluations.

• Guide internal teams and partners on scaling, monitoring, and deploying AI platforms into the cloud.

• Serve as a senior technical advisor to Oracle hardware, software, cloud, and support teams.

• Act as the final level of engineering support for complex deployed product issues.

• Assist with root-cause analysis through lab replication, remote debug, and…