Graphcore - System Test Manager - Hardware

• Lead and grow a multidisciplinary team of hardware and software test engineers delivering manufacturing test solutions for complex compute systems. • Define the manufacturing test strategy and roadmap for High Performance Modules, Server Blades, and Multi-node racks. • Own delivery of test executive software used in both manufacturing and lab environments to orchestrate test sequencing, logging, results aggregation, and integration of test content from diverse sources. • Partner with internal software, firmware, and platform teams to ensure required hooks, diagnostics, telemetry, and APIs exist to enable effective manufacturing test. • Establish best practices for test coverage, traceability, release management, and configuration control of test software and content. • Implement metrics and dashboards for manufacturing test (yield, escapes, false fails, coverage, cycle time) and lead continuous improvement initiatives. • Drive root-cause analysis of manufacturing failures and field returns, coordinating corrective actions across design, validation, and manufacturing engineering. • Own the delivery of manufacturing test fixtures for High Performance Modules and Server Blades, including defining requirements, managing external subcontractors, and ensuring fixtures meet quality, cost, schedule, and production readiness needs. • Ensure test solutions are scalable, maintainable, and production-ready, including documentation, training, and support processes for factory deployment. • Support supplier/contract manufacturing engagements as needed, including test station readiness, deployment qualification, and ongoing production support. • Candidate Profile • Candidate Profile • Essential: • Experience developing manufacturing test solutions for high-performance servers, accelerators (GPU-class), or comparable large scale compute hardware. • Demonstrated people leadership experience managing a mixed hardware/software engineering team (hiring, coaching, performance management, and team development). • Deep technical understanding across silicon, board, and system design sufficient to define effective manufacturing test coverage and guide debug/root-cause analysis. • Strong cross-functional collaboration skills, with experience driving requirements and delivery with internal software/firmware/platform teams to enable testability. • Hands-on experience using Linux, OpenBMC, and vendor specific test tools, diagnostics, and system-level utilities to test hardware in lab and manufacturing environments. • Experience with scripting languages such as Python, Bash, or similar. • Desirable: • Familiarity with rack-scale/multi-node systems, high-speed interconnects, and production qualification of complex assemblies. • Experience improving manufacturing KPIs (yield, test time, false fail reduction) through data-driven process and test optimization. • Knowledge of open-source tools commonly used for manufacturing test