Senior Performance Architect, Heterogeneous Workload Optimization

What you'll do

• Architect and maintain custom profiling frameworks for unified CPU and GPU execution views.
• Conduct deep-dive benchmarking of EDA applications to characterize memory access patterns and cache hit rates.
• Use GPU profilers to detect warp divergence, sub-optimal occupancy, and PCIe/NVLink bottlenecks.
• Develop tools to monitor and attribute high-watermark memory usage in multi-terabyte EDA builds.
• Identify opportunities for data structure compression and smarter memory pooling.
• Develop predictive models to guide hardware procurement and cloud instance selection based on algorithmic complexity.
• Analyze interactions between extensive design graphs in system memory and high-throughput GPU kernels.

What we're looking for

• A BS, MS, or PhD in Computer Science, Electrical Engineering, or a related field (or equivalent experience).
• More than 8 years of relevant experience.
• At least 5 years of experience involved in systems-level performance analysis.
• Grasp of the CUDA programming model and experience using GPU profiling tools like NVIDIA Nsight Systems/Compute.
• Extensive knowledge of profiling tools such as perf, eBPF, VTune, or Valgrind.
• Experience with distributed compute environments such as Slurm, LSF, or Kubernetes.
• Ability to distill sophisticated performance data into actionable engineering roadmaps.