Principal Reliability Scientist
Graphcore is a SoftBank-owned AI-compute company developing AI processors, systems, and software for machine-learning workloads.
Funding history
About Graphcore
Graphcore develops Intelligence Processing Units (IPUs) and the Poplar SDK for building and running machine-learning applications. It continues operating under the Graphcore name as a wholly owned SoftBank Group subsidiary.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will define reliability requirements and apply reliability methods across silicon, boards and systems. You will design experiments, analyse experimental, field and manufacturing data, and use findings to guide design decisions, reliability targets and spares strategies. You will lead root-cause investigations and communicate reliability risks and recommendations to stakeholders.
Requirements
- Background in reliability engineering or reliability science in semiconductor, hardware or complex-systems environments
- Experience with physics-of-failure approaches in high-performance computing, AI hardware or related domains
- Experience with reliability modelling, experimental design and statistical data analysis
- Ability to interpret experimental reliability data to drive engineering decisions
- Experience with MTBF, MTTR, RAS and failure-rate analysis
- Ability to lead technically challenging investigations independently
- Communication skills to influence design and operations teams using data-driven insights
Responsibilities
- Define and refine reliability requirements across silicon, board and system levels
- Apply reliability methodologies to complex systems including liquid-cooled architectures
- Design and execute reliability and performance experiments
- Analyse experimental, field and manufacturing data for reliability metrics
- Inform product design trade-offs, reliability targets and spares provisioning strategies
- Influence architecture and component selection using reliability considerations
- Develop system-level reliability models incorporating thermal, mechanical and fluid behaviour
- Lead root-cause investigations and drive corrective and preventative actions
- Improve reliability tools, processes and best practices
- Communicate reliability concepts, risks and recommendations to stakeholders