Hardware Validation and Debug Engineer

About the role

Graphcore develops specialized semiconductors and data center hardware to advance artificial intelligence computing. As a SoftBank Group company, we are growing our Bristol labs to focus on the bring-up and verification of our next generation of system platforms. This role places you at the heart of that expansion, owning the critical tasks that transform silicon design into reliable, production-ready hardware. You will be responsible for leading complex debugging initiatives that require a deep understanding of electronic systems and meticulous attention to detail. Success in this position means directly enabling the performance and stability of the hardware that powers Graphcore's machine learning solutions. The position demands a proactive mindset capable of navigating intricate technical challenges from initial power-on to full system validation. You will work closely with cross-functional partners to ensure that hardware issues are resolved efficiently and comprehensively. This role is fundamental to de-risking our development programs and ensuring our platforms meet the highest standards of quality and reliability.

Key facts

What you'll do

• Execute the bring-up and verification flow for nascent hardware platforms, methodically progressing from initial power to full system operation.
• Probe and rectify anomalies concerning PCBs, power delivery networks, signal paths, and diverse system interfaces to ensure robust functionality.
• Conduct exhaustive validation of LPDDR5-9600 memory systems, encompassing initialization sequences, training procedures, margin analysis, and long-term stability verification.
• Carry out detailed signal integrity investigations utilizing eye diagram analysis and precise DDR timing margin evaluations to quantify system performance.
• Isolate root causes for intricate hardware malfunctions and firmware anomalies, then coordinate with multidisciplinary teams to engineer and deploy effective solutions.
• Author comprehensive technical documentation, including detailed test procedures, step-by-step bring-up guides, and thorough debug reports for future reference.
• Partner with architecture and firmware teams to correlate hardware behavior with system-level requirements and performance targets.
• Drive the characterization and optimization of board-level metrics to ensure compliance with defined specifications and industry standards.
• Mentor junior engineers on best practices for debug methodology and the use of validation tools within the development lifecycle.
• Continuously assess and refine debug workflows to improve efficiency, traceability, and the overall quality of the bring-up process.

Requirements

• Demonstrate proven experience in hardware debugging and complex low-level system integration across multiple project cycles.
• Exhibit deep expertise in LPDDR validation methodologies, including intricate tuning activities and rigorous compliance testing procedures.
• Show proficiency in advanced signal integrity analysis techniques and protocol-level troubleshooting for high-speed digital systems.
• Illustrate the ability to perform independent board bring-up and subsystem debugging with minimal supervision and high reliability.
• Possess strong skills in root-cause analysis, employing systematic methodologies to drive issue resolution across cross-functional engineering teams.
• Demonstrate experience using a wide array of lab instrumentation, including high-bandwidth oscilloscopes, BERT systems, and VNA/TDR equipment.
• Hold a strong understanding of digital logic concepts and the interaction between hardware and firmware during the boot and execution phases.
• Have a track record of working effectively in a fast-paced, dynamic environment where priorities can shift rapidly based on project needs.

Nice to have

• Familiarity with PCBA and broader system-level technologies and their implications for debug strategies.
• Experience validating high-speed Ethernet and PCIe interfaces, including protocol analysis and compliance checks.
• Knowledge of ATE systems and their operational capabilities within a production or development validation context.
• Proficiency in scripting or coding for automation and data analysis using Python, LabView, or BASH to enhance test efficiency.

Skills & tools

• Hardware debug
• LPDDR5-9600
• SPI/I2C/I3C/UART
• Signal integrity analysis
• Lab instrumentation (Oscilloscopes, BERT, VNA/TDR)

Practical notes

Graphcore provides a competitive salary and benefits package. We are an equal opportunity employer committed to an inclusive workplace. We offer flexible interview arrangements and can provide reasonable adjustments upon request.

About the company

Graphcore has built a new type of processor for machine intelligence to accelerate machine learning and AI applications for a world of intelligent machines.