← Serch more jobs

Performance Modeling Architect, HBM

LinkedIn Micron Technology Folsom, CA
Not Applicable Posted April 3, 2026 Job link
Thinking about this job
Not Met Priorities
What still needs stronger evidence
Requirements
  • Strong understanding of GPU/accelerator architecture and system-level design fundamentals.
  • Deep knowledge of memory hierarchy (caches / SRAM / NoC / HBM / DRAM) and AI workload behavior.
  • Hands-on experience with performance analysis and/or modeling of GPU/accelerator systems.
  • Proficiency in C++ and Python; experience with CUDA; familiarity with ML frameworks (e.g., TensorFlow or PyTorch).
  • Strong experience in performance modeling, system modeling, or architectural analysis.
  • Solid understanding of memory subsystem architecture, especially HBM, DRAM, and high‑bandwidth interfaces.
  • Experience analyzing system‑level performance tradeoffs (bandwidth vs latency, power vs performance, area vs scalability).
  • Proficiency in model development using C++, Python, SystemC, or similar languages.
  • Familiarity with SoC architecture, memory controllers, interconnects, and IP integration.
  • Experience correlating models with RTL, emulation, or silicon measurements.
  • Experience optimizing at a low level (e.g., PTX/SASS) and/or using GPU profiling tools.
  • Publications or research contributions in AI hardware acceleration, memory systems, or rack-scale architecture.
Preferred Skills
  • Proficiency in C++ and Python; experience with CUDA; familiarity with ML frameworks (e.g., TensorFlow or PyTorch).
  • Strong experience in performance modeling, system modeling, or architectural analysis.
  • Solid understanding of memory subsystem architecture, especially HBM, DRAM, and high‑bandwidth interfaces.
  • Experience analyzing system‑level performance tradeoffs (bandwidth vs latency, power vs performance, area vs scalability).
  • Proficiency in model development using C++, Python, SystemC, or similar languages.
  • Familiarity with SoC architecture, memory controllers, interconnects, and IP integration.
  • Experience correlating models with RTL, emulation, or silicon measurements.
  • Experience optimizing at a low level (e.g., PTX/SASS) and/or using GPU profiling tools.
  • Publications or research contributions in AI hardware acceleration, memory systems, or rack-scale architecture.
Education
  • (Not required) – PhD in Computer Architecture, Electrical/Computer Engineering, or related field (or MS with 3+ years of relevant experience).