Description
The Senior Reliability Scientist leads reliability activities across Graphcore’s complex, high-performance hardware systems. The role defines reliability requirements, applies physics-of-failure and reliability-modelling methods, designs and analyses experiments, evaluates metrics such as MTBF, MTTR, RAS, and soft-error rates, supports system-level reliability models, leads root-cause investigations, and advises design and operations teams on reliability trade-offs and spares provisioning. The position requires a strong background in reliability engineering or science, experience with high-performance computing or AI hardware, and expertise in reliability modelling, experimental design, and statistical data analysis.
