Principal Reliability Scientist
Graphcore is a Bristol-based AI chipmaker (IPU accelerators), a SoftBank subsidiary and a Molten Ventures portfolio company.
Maintainer signals as of 8/14/2026
About Graphcore
Graphcore (graphcore.ai) is a British semiconductor company building Intelligence Processing Units (IPUs) for AI workloads. Founded in Bristol in 2016, it was acquired by SoftBank in 2024. It is a portfolio company of Molten Ventures.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will lead reliability activities for complex high-performance systems, defining reliability requirements, designing statistically rigorous experiments, and analyzing experimental, field, and manufacturing data. You will build reliability models, investigate root causes, influence architecture and component choices, develop reliability processes and tools, and communicate data-driven recommendations to design and operations stakeholders.
Requirements
- Reliability engineering
- Reliability science
- Semiconductor
- Hardware
- Complex systems
- Physics of failure
- High-performance computing
- AI hardware
- Reliability modelling
- Experimental design
- Statistical data analysis
- MTBF
- MTTR
- RAS
- Failure rate analysis
- Root cause investigation
- Liquid cooling
- Fluid dynamics
- Soft error mechanisms
- SER modelling
Responsibilities
- Define reliability requirements across silicon, board, and system levels
- Apply reliability methodologies to complex systems
- Design and execute reliability experiments
- Analyze experimental, field, and manufacturing data
- Quantify MTBF, MTTR, RAS, and soft error rates
- Inform design trade-offs and reliability targets
- Develop system-level reliability models
- Lead root cause investigations
- Drive corrective and preventative actions
- Improve reliability tools, processes, and practices
- Communicate reliability risks and recommendations