Senior Resiliency Architect, Hardware Diagnostics and Resiliency Modeling
Core
Develop hardware diagnostics software and resiliency models for NVIDIA GPUs and SoCs to identify defects, analyze field data, and ensure reliability for AI workloads in datacenters and edge computing.
Role type
Senior IC hardware resiliency architect
Builds
Diagnostics software suites, RAS models, automation tooling, and analytics dashboards for GPU/SOC reliability
Domain
Semiconductor hardware reliability and AI infrastructure
Required skills
GPU architecture knowledge, hardware diagnostics, RAS metrics modeling (FIT, AVF), Python scripting, C/C++, CUDA programming, data mining, automation, statistical analysis
Preferred skills
Embedded software development, visualization tools, statistical judgment on exposure-adjusted rates, resiliency trade-off analysis in AI datacenters
Technologies
Python, SQL, C/C++, CUDA, container-based job execution
Responsibilities
Develop diagnostics software to stress test GPUs/SOCs and identify hardware defects; Analyze coverage gaps in diagnostic suites and enhance test repeatability; Model and analyze RAS metrics (FIT, Availability) to drive hardware/software improvements; Analyze field data on hardware interruptions to correlate with RAS models; Design automation scripts to manage diagnostic jobs across compute clusters; Develop dashboards integrating diverse data sources for insights; Collaborate with engineering teams to categorize cluster failures
Seniority
Senior, hands-on IC
