Principal Performance Architect

Microsoft Microsoft · Big Tech · Mountain View, CA +4 · Silicon Engineering

The Principal Performance Architect will analyze performance bottlenecks in SoC for critical AI workloads, prototype optimizations for AI accelerators, and develop/test SoC and IP models. This role focuses on the performance and power efficiency of hardware infrastructure for AI computations.

What you'd actually do

  1. Use models to analyze performance bottlenecks in SoC for critical AI workloads
  2. Prototype opportunities for performance and power optimizations, and trade-offs on AI accelerators
  3. Develop and test SoC and IP models, including model integration
  4. Continuous collaboration with design and performance verification teams to close on SoC performance

Skills

Required

  • Doctorate in Electrical Engineering, Computer Engineering, Computer Science, or related field AND 3+ years technical engineering experience OR Master's Degree in Electrical Engineering, Computer Engineering, Computer Science, or related field AND 6+ years technical engineering experience OR Bachelor's Degree in Electrical Engineering, Computer Engineering, Computer Science, or related field AND 8+ years technical engineering experience OR equivalent experience

Nice to have

  • Doctorate in Electrical Engineering, Computer Engineering, Computer Science, or related field AND 5+ years technical engineering experience OR Master's Degree in Electrical Engineering, Computer Engineering, Computer Science, or related field AND 8+ years technical engineering experience OR Bachelor's Degree in Electrical Engineering, Computer Engineering, Computer Science, or related field AND 12+ years technical engineering experience OR equivalent experience
  • 1+ year(s) experience working on or leading projects from beginning-to-end
  • 4+ years of experience with Python, C, C++
  • 6+ years of experience with performance modeling at various levels of abstraction, and analysis
  • Experience in architecture and workload analysis on GPUs

What the JD emphasized

  • critical AI workloads
  • AI accelerators

Other signals

  • AI workloads
  • AI accelerators
  • performance modeling
  • SoC performance