Server CPU Hardware Systems Lead

About the role

Graphcore is actively seeking a Lead System Engineer to manage the validation of compute blade and rack infrastructure for our next-generation AI compute systems. In this capacity, you will own the full validation lifecycle, directing activities from initial bring-up through to volume production support for ARM-based server architectures. The role requires you to act as the primary technical authority for system-level issues, ensuring that hardware and software components integrate seamlessly to meet strict architecture specifications. You will be responsible for establishing and maintaining robust methodologies that govern the interaction between firmware, software, and hardware across the entire compute stack. This position demands a high degree of ownership, requiring you to solve complex, multi-domain problems that span electrical, mechanical, and software disciplines. You will work closely with cross-functional teams to translate product requirements into concrete test plans and validation procedures. Ultimately, your work will directly determine the stability, performance, and reliability of the systems that power our AI platform.

Key facts

What you'll do

• Lead system enablement activities for first silicon and firmware, ensuring alignment with architecture specifications and performance targets.
• Define and standardize organization-wide methodologies for the integration of hardware, firmware, and software components across validation teams.
• Design, build, and maintain the lab hardware and software toolchains necessary to support blade and rack-level validation efforts.
• Triage, isolate, and resolve complex technical issues that arise during post-silicon debugging and production validation phases.
• Create comprehensive test plans that validate the functionality of CPU, GPU, memory, HBM, and IO subsystems under diverse conditions.
• Innovate validation procedures and develop advanced scripting tools to improve test coverage, reduce cycle times, and enhance overall quality metrics.
• Collaborate with global engineering teams to coordinate validation schedules, share knowledge, and resolve dependencies across regions.
• Partner with product management to ensure that validation activities support program milestones and release criteria.
• Document all validation results, failure modes, and corrective actions to create a clear audit trail for compliance and future development.
• Drive the adoption of best practices for platform-level debug, leveraging deep expertise in system BIOS, device drivers, and OS interactions.

Requirements

• Possess an extensive background in first silicon and system bring-up, with demonstrable experience managing OS, firmware, and hardware validation tasks.
• Maintain a deep knowledge of ARM or X86 architectures, SoC design principles, RAS mechanisms, and advanced power management strategies.
• Demonstrate proficiency with industry-standard buses such as PCIe and CXL, including protocol analysis and signal integrity considerations.
• Have hands-on experience enabling storage and networking capabilities, including the configuration of DNS and DHCP services in lab environments.
• Show expertise in platform-level debug techniques, device driver integration, system BIOS configuration, and the interaction between BIOS and operating systems.
• Exhibit a strong command of Linux and Windows operating systems, along with hypervisors such as VMware, KVM, and Hyper-V.
• Prove strong technical program management skills, including the ability to coordinate effectively with global teams and manage competing priorities.
• Demonstrate a thorough understanding of datacenter technology stacks and development certification processes to ensure compliance and quality.
• Hold the ability to interpret complex technical documentation and translate it into actionable validation steps for engineering teams.
• Display strong written and verbal communication skills, allowing you to convey intricate technical concepts to both technical and non-technical stakeholders.

Nice to have

• Hold a Masters or PhD degree in Electrical Engineering, Computer Engineering, or a closely related technical field.
• Bring 14 or more years of experience in server compute rack or datacenter blade validation roles.
• Have direct experience with the design and deployment of modern AI and ML rack-scale systems at scale.
• Show familiarity with ODM partner collaboration and established hardware development best practices.
• Possess a background in automated test frameworks and continuous integration pipelines for hardware validation.

Practical notes

This is a full-time position based in Austin, Texas, United States. The role may require travel to support validation activities at various sites as needed. Employment is contingent upon the successful completion of all required background checks. Graphcore is committed to providing reasonable adjustments during the interview process to support candidates with disabilities or specific requirements.