Senior System Diagnostics Engineer – AI Hardware

Graphcore; Austin (TX); On-site; USD 180,000 - 240,000; Full time

Benefits offered by this job

Medical, dental and vision coverage

FSAs and HSAs

401(k) retirement plan

Commuter benefits

Wellness services

Employee Assistance Programme (EAP)

Job summary

Graphcore seeks a seasoned System Tests & Diagnostics Engineer to develop and extend silicon validation tools for its AI SoCs. You will build diagnostics and stress tools that reveal hardware failures and characterize silicon behavior, while collaborating with Arm and Graphcore teams across hardware, firmware, and validation.

You will deliver reusable utilities, improve platform observability during bring-up and validation, and design configurable diagnostics for multiple silicon revisions and

Qualifications

• Bachelor's or Master's degree in Computer Science, Computer Engineering, Electrical Engineering, or related field.
• 10+ years building hardware diagnostics, system validation software, or low-level systems software.
• Strong Python and C/C++ development skills.
• Solid Linux systems experience.
• Deep understanding of server platform architecture and interactions across CPU, memory, PCIe, firmware, and drivers.
• Experience debugging hardware/software interactions across multiple layers.
• Experience with diagnostics, stress testing, or hardware validation software.
• Experience with server platforms, embedded systems, or SoC validation.
• Strong analytical and debugging abilities and excellent communication.
• Proven ability to collaborate across hardware, firmware, software, and validation teams.

Responsibilities

• Learn and extend Arm diagnostics tools to support Graphcore AI platform.
• Develop specialized diagnostics and stress-testing software for CPU, memory, interconnect, and PCIe.
• Build reusable validation utilities integrated into the existing framework.
• Develop tools exposing intermittent hardware failures including SDC, timing issues, and instability.
• Design configurable diagnostics supporting multiple silicon revisions and environments.
• Automate diagnostics across server and rack-scale validation environments.
• Collaborate with hardware architects to understand new capabilities and missing diagnostics.
• Work with firmware and validation to improve hardware observability.
• Debug low-level hardware, firmware, OS, and driver interactions.
• Analyze diagnostic output and improve fault isolation methods.
• Deliver configurable diagnostics that scale across platforms and revisions.
• Create reusable libraries to boost productivity across validation teams.

Skills

Python

C/C++

Linux

System validation

Debugging

Diagnostics

Communication

Collaboration

Problem solving

Server architecture knowledge

Education

Bachelor's or Master's degree in CS/CE/EE

Tools

Arm-based server platforms

PCIe diagnostics tools

Silicon bring-up tooling

Git

Job description

Graphcore seeks a seasoned System Tests & Diagnostics Engineer to develop and extend silicon validation tools for its AI SoCs. You will build diagnostics and stress tools that reveal hardware failures and characterize silicon behavior, while collaborating with Arm and Graphcore teams across hardware, firmware, and validation.

You will deliver reusable utilities, improve platform observability during bring-up and validation, and design configurable diagnostics for multiple silicon revisions and