About us
Graphcore is one of the world’s leading innovators in Artificial Intelligence compute.
It is developing hardware, software and systems infrastructure that will unlock the next generation of AI breakthroughs and power the widespread adoption of AI solutions across every industry.
As part of the SoftBank Group, Graphcore is a member of an elite family of companies responsible for some of the world’s most transformative technologies.
Graphcore’s teams are drawn from diverse backgrounds and bring a broad range of skills and perspectives.
Job Summary
We are seeking a Staff System Validation Engineer to design and implement validation tests for Arm-based data center SoCs using a combination of open-source benchmarking tools and custom micro-benchmarks. Define test cases, tune workload parameters, and use Python to automate and analyze validation across processing units, system memory, communication links, and PCI Express components.
The Team
The Systems Validation team validates Graphcore’s AI compute platforms across hardware, firmware, and software domains.
Responsibilities and Duties
- Objectives, workload models, parameters, metrics, and pass/fail criteria.
- Stress-ng, fio, iperf, sysbench, Imbench
- Concurrency (threads/cores), memory footprint, access patterns
- Queue depth, block size, CPU/NUMA affinity.
- Functional, performance, stress, and corner-case testing.
- CPU scaling and cache behavior
- Memory (DDR/HBM) bandwidth, latency, and NUMA effects
- Interconnect contention under multi-core load
- PCIe/I-O throughput, latency, and multi-device scenarios
- Develop custom micro-benchmarks (C/C++) when existing tools are insufficient
- Automate test execution and orchestration
- Implement parameter sweeps and test matrices
- Parse, analyze, and visualize results.
- Debug system behavior and performance issues in collaboration with hardware and firmware teams
Candidate Profile
Essential:
- Strong background in Linux systems and low-level performance analysis
- Experience in system validation, benchmarking, or performance testing
- CPU architecture, memory systems, or PCIe
- Experience using benchmarking tools (stress-ng, fio, iperf, etc.)
- Ability to define test cases, parameters, and workload models
- Proficiency in Python (essential) for automation, orchestration, and data analysis
- Programming experience in C/C++ for micro-benchmark development
Desirable:
- Experience with Arm-based platforms
- Strong programming skills in C/C++ and Python for system-level development and automation
- Familiarity with performance tools (perf, numactl, taskset)
- Experience with large-scale or high core-count systems