Staff Hardware System Test Engineer

About the role

This position is focused on developing manufacturing test solutions for complex compute systems to ensure high quality and reliability across the product lifecycle. The hire will own the definition of testing strategies for Host Processor Modules, server blades, and multi-node racks in collaboration with cross-functional teams. You will create test software, design testing approaches, and resolve hardware issues across the entire stack from silicon to data center deployment. The role requires leading technical workstreams and driving engineering standards across the organization without direct line management responsibilities. You will perform hands-on investigation and root-cause analysis across silicon, boards, and systems to resolve complex failures. Collaboration with hardware, firmware, software, and manufacturing teams is central to improving test coverage and process efficiency. This role is critical in bridging engineering disciplines to deliver scalable and robust test methodologies. The successful candidate will act as a technical leader in ensuring that manufacturing test solutions are both effective and efficient.

Key facts

What you'll do

• Create test software, design testing approaches, and resolve hardware issues for complex compute systems.
• Collaborate with hardware, firmware, software, and manufacturing teams to improve test coverage and streamline validation flows.
• Lead technical workstreams and drive engineering standards across the organization to ensure consistency and quality.
• Perform hands-on investigation and root-cause analysis across silicon, boards, and systems to identify failure mechanisms.
• Develop and maintain test infrastructure and automation frameworks to support high-volume manufacturing environments.
• Define test strategies for Host Processor Modules, server blades, and multi-node racks to validate functionality and performance.
• Utilize Linux, OpenBMC, and vendor-specific diagnostic utilities in lab and production environments to debug issues.
• Optimize manufacturing KPIs such as yield and test time through statistical analysis and data-driven decisions.
• Design testability features such as telemetry and self-test hooks into products to improve debug and coverage.
• Contribute to the development and maintenance of open-source tools for system bring-up and hardware diagnostics.
• Work closely with software engineers to ensure firmware and boot flows are testable and reliable in manufacturing.
• Support the qualification and validation of new hardware platforms through comprehensive test plan development.
• Act as a technical expert in manufacturing debug sessions to resolve complex system-level issues.
• Mentor junior engineers and collaborate across teams to foster a culture of technical excellence and ownership.

Requirements

• Significant experience developing and deploying manufacturing test solutions for high-performance servers, GPU-class accelerators, or similar large-scale compute hardware.
• Proven technical leadership as an individual contributor, including owning workstreams and collaborating across teams without direct line management.
• Deep technical understanding of silicon, board, and system design to lead debug efforts and root-cause analysis.
• Strong software engineering skills in scripting and automation using Python or Bash to develop test tools and workflows.
• Proficiency with Linux, OpenBMC, and vendor-specific diagnostic utilities in both lab and production environments.
• Experience with hardware debug techniques and the use of diagnostic tools at the silicon and board level.
• Strong analytical and problem-solving skills with the ability to dissect complex system failures.
• Excellent communication skills to collaborate effectively with cross-functional teams and stakeholders.

Nice to have

• Familiarity with rack-scale or multi-node systems and high-speed interconnects.
• Experience optimizing manufacturing KPIs like yield and test time through statistical analysis.
• Knowledge of open-source tools for system bring-up and hardware diagnostics.
• Experience designing testability features such as telemetry and self-test hooks into products.

Practical notes

• Benefits include unlimited annual leave, up to 5% matched pension, phantom equity, and flexible working arrangements.
• Additional perks include a health cash plan, income protection, life assurance, and optional private medical or dental plans.
• The company provides on-site food and an on-site barista.
• Graphcore is part of the SoftBank Group.
• The company is an equal opportunity employer and provides interview adjustments upon request.
• This is a full-time position based in Bristol, UK, or Cambridge, United Kingdom.
• Candidates must be eligible to work in the United Kingdom without sponsorship.
• No specific hours are stated, but the role operates within standard full-time working hours.
• Travel is not required as part of the standard duties for this role.
• Visa sponsorship is not available for this position.
• The application process will close once the role is filled or upon company decision.