SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Graphcore, part of the SoftBank Group, is seeking a Senior System Tests & Diagnostics Engineer to develop, extend, and integrate specialized silicon validation and diagnostics tools for next-generation AI SoCs. This role focuses on developing diagnostic software and stress tools that expose hardware failures, characterize silicon behavior, and improve platform observability—distinct from traditional validation roles that execute test plans.
You will work with existing Arm-developed diagnostics technologies and extend them to support Graphcore's next-generation AI silicon. You will be responsible for developing system-level diagnostics and stress tools that integrate with an existing framework to detect data integrity, computational correctness, performance, and reliability issues across CPUs, AI accelerators, memory, storage, PCIe, firmware, BMC, and other platform components. Examples include silent data corruption (SDC) tests, power transient stress tools, and platform diagnostics, with opportunities to develop new diagnostics as future hardware capabilities evolve.
Key responsibilities include: learning and extending existing Arm diagnostics tools; developing specialized diagnostics and stress-testing software for CPU, memory, interconnect, PCIe, and other system components; building reusable validation utilities that integrate into the existing validation framework; developing tools that expose intermittent hardware failures including silent data corruption and timing-related issues; designing configurable diagnostic applications supporting multiple silicon revisions and platforms; developing automation for executing diagnostics across server and rack-scale validation environments; collaborating with hardware architects to understand new hardware capabilities and identify missing diagnostics; working closely with firmware and validation teams to improve hardware observability; debugging low-level hardware, firmware, operating system, and driver interactions; analyzing diagnostic output and improving fault isolation methodologies; developing software that enables engineers to reproduce and investigate difficult hardware failures; and contributing reusable libraries and utilities that improve engineering productivity across multiple validation teams.
This role requires close collaboration with hardware architects, firmware engineers, validation engineers, and diagnostics teams to understand new hardware capabilities and translate them into reusable diagnostic software.
Success in this role means extending existing diagnostics technologies to support new Graphcore hardware, developing new diagnostics tools for emerging hardware capabilities, building reusable software components that integrate seamlessly with the existing validation framework, improving hardware observability and root-cause isolation, detecting and characterizing intermittent hardware failures that traditional validation techniques cannot expose, delivering configurable diagnostics that scale across multiple platforms and silicon revisions, and working effectively across hardware, firmware, validation, and diagnostics teams to continuously improve platform quality.
REQUIREMENTS:
Essential:
- Bachelor's or Master's degree in Computer Science, Computer Engineering, Electrical Engineering, or a related technical discipline
- 12+ 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
Desirable:
- Arm-based server platforms
- AI accelerators or high-performance computing systems
- Silent Data Corruption (SDC) testing
- Hardware stress testing
- Power transient analysis
- Hardware fault injection methodologies
- Firmware validation
- Silicon bring-up
- Performance characterization
- Hardware telemetry and observability
- BMC firmware or server management
- RAS (Reliability, Availability, Serviceability) technologies
- Validation across subsystems: CPU scaling and cache behavior, memory (DDR/HBM) bandwidth/latency/NUMA effects, interconnect contention under multi-core load, PCIe/I-O throughput/latency/multi-device scenarios, high-speed I/O validation