System Hardware Reliability Engineer

Job description

Design and implement Prognostics and Health Management (PHM) algorithms using physics-informed machine learning to forecast hardware degradation and Remaining Useful Life (RUL). Develop stochastic degradation models to predict the impact of dynamic thermal and power envelopes on fleet reliability. Build health state monitoring and anomaly detection frameworks leveraging massive fleet telemetry data to enable predictive maintenance. Partner with software and controls teams to integrate predictive health models into automated load-management and thermal capping mechanisms. Lead comprehensive reliability assessments and PoF modeling for silicon, interconnects, optics, thermal solutions and power delivery/battery systems. Drive Failure Modes and Effects Analyses (FMEAs) to identify vulnerabilities under extreme environmental operating conditions. Minimum Qualifications: Bachelor’s degree in Reliability Engineering, Data Science, Mechanical/Electrical Engineering, Applied Physics, or equivalent practical experience. 8 years of experience in applying Design for Reliability techniques, and working on multiple consumer electronics products. 8 years of experience in hardware reliability engineering, physics of failure, and predictive analytics. Preferred Qualifications: Master’s degree in Reliability Engineering, Data Science, Mechanical/Electrical Engineering, Applied Physics, or equivalent practical experience. 7 years of experience with experimental design and execution of complex hardware products. 6 years of statistical analysis experience. 6 years of experience working with manufacturing partners. 5 years of experience with failure analysis techniques. Expertise in physics-informed machine learning, Bayesian analysis, and utilizing frameworks like PyTorch or TensorFlow for reliability forecasting.