Staff System Tests & Diagnostics Engineer

Graphcore•Austin, TX

17h•Hybrid

About The Position

Graphcore is a leading innovator in Artificial Intelligence compute, developing hardware, software, and systems infrastructure to drive AI breakthroughs and widespread adoption. As part of the SoftBank Group, Graphcore is committed to enabling Artificial Super Intelligence and making its benefits accessible to all. The company fosters a culture of continuous learning and innovation, with teams drawn from diverse backgrounds, including AI research specialists, silicon designers, software engineers, and systems architects. The team is responsible for developing and applying system-level diagnostics and validation capabilities to ensure the quality and reliability of Graphcore’s AI computing platforms. They work closely with hardware architects, firmware engineers, validation engineers, and software teams to create reusable diagnostic software that exercises complete systems and provides the necessary observability for understanding complex hardware and software interactions. Their work encompasses silicon bring-up, system validation, stress testing, fault isolation, and platform characterization.

Requirements

Bachelor's or Master's degree in Computer Science, Computer Engineering, Electrical Engineering, or a related technical discipline.
8+ years of experience developing hardware diagnostics, system validation software, firmware validation tools, or low-level systems software.
Strong software development skills in Python and C/C++.
Strong Linux systems experience.
Strong understanding of modern server platform architecture, including how CPU, memory, PCIe, storage, networking, firmware, operating system, and device drivers interact within a complete system.
Experience debugging hardware/software interactions across multiple layers of the platform.
Experience developing diagnostics, stress testing, or hardware validation software.
Experience with server platforms, embedded systems, or SoC validation.
Strong analytical and debugging skills.
Experience collaborating across hardware, firmware, software, and validation teams.
Excellent communication and problem-solving skills.

Nice To Haves

Experience with Arm-based server platforms
Experience with AI accelerators or high-performance computing systems
Experience with Silent Data Corruption (SDC) testing
Experience with Hardware stress testing
Experience with Power transient analysis
Experience with Hardware fault injection methodologies
Experience with Firmware validation
Experience with Silicon bring-up
Experience with Performance characterization
Experience with Hardware telemetry and observability
Experience with BMC firmware or server management
Experience with RAS (Reliability, Availability, Serviceability) technologies
Validate across subsystems: CPU scaling and cache behavior
Validate across subsystems: Memory (DDR/HBM) bandwidth, latency, and NUMA effects
Validate across subsystems: Interconnect contention under multi-core load
Validate across subsystems: PCIe/I-O throughput, latency, and multi-device scenarios
Validate across subsystems: High-speed I-O validation

Responsibilities

Develop, extend, and integrate specialist silicon validation and diagnostic software for Graphcore’s AI computing systems.
Create diagnostic and stress-testing capabilities to expose hardware failures, characterize system behavior, and improve platform observability during silicon bring-up and validation.
Independently lead complex diagnostic development activities, working across hardware, firmware, and software boundaries.
Improve tools and methodologies for identifying, reproducing, and isolating challenging system-level issues.
Design, develop, and extend system-level diagnostic and stress-testing software for Graphcore AI computing platforms.
Develop diagnostic applications covering processors, memory, interconnects, PCIe, storage, networking, and other system components.
Build reusable validation utilities and libraries that integrate with Graphcore’s system validation infrastructure.
Develop tools to identify and characterize intermittent hardware failures, including data integrity issues, timing-related failures, and system instability.
Design configurable diagnostic applications capable of supporting multiple silicon revisions, platforms, and execution environments.
Develop automation for executing diagnostics across server and rack-scale validation environments.
Create configuration-driven diagnostic capabilities for scalable parameterization, workload variation, and repeatable testing.
Work with hardware architects and engineering teams to understand new hardware capabilities and identify opportunities for additional diagnostic coverage.
Collaborate with firmware and validation engineers to improve platform observability and fault isolation.
Debug complex interactions between hardware, firmware, operating systems, and device drivers.
Analyze diagnostic results, identify failure patterns, and develop improved methods for reproducing and isolating system-level issues.
Develop software and tooling to enable engineering teams to efficiently reproduce, investigate, and resolve difficult hardware failures.
Contribute reusable software components and engineering practices to improve productivity and diagnostic capability across validation teams.
Provide technical guidance and collaborate across engineering disciplines to solve complex system validation and diagnostic problems.
Extend existing diagnostics technologies to support new Graphcore hardware.
Develop new diagnostics tools for emerging hardware capabilities.
Build reusable software components that integrate seamlessly with the existing validation framework.
Improve hardware observability and root-cause isolation.
Detect and characterize intermittent hardware failures that traditional validation techniques cannot expose.
Deliver configurable diagnostics that scale across multiple platforms and silicon revisions.
Work effectively across hardware, firmware, validation, and diagnostics teams to continuously improve platform quality.