Senior AI Performance Architect
Core
Analyze frontier AI training and inference workloads to identify performance bottlenecks and develop analytical models, simulators, and tools for AI system performance optimization.
Role type
Senior IC AI Performance Architect
Builds
Analytical models, simulators, data-analysis tools, and architecture decision materials for large-scale AI systems
Domain
AI Systems Performance, Computer Architecture, High-Performance Computing
Deliverable
production ML models
Required skills
Performance modeling, simulation, profiling, workload characterization, system performance analysis, Python programming, C++, CUDA, distributed execution strategies, transformer-based model optimization, hardware-software co-design, root-cause analysis, data visualization
Preferred skills
Experience with silicon measurements, accelerator architecture, HBM, scale-up/scale-out networks, compilers, runtimes, microbenchmarking
Technologies
Python, C++, CUDA, Triton, ROCm/HIP, Transformer models, LLMs, Tensor parallelism, Pipeline parallelism, Expert parallelism, Data parallelism, PCIe, HBM
Responsibilities
Analyze frontier training and inference workloads to identify key performance requirements and bottlenecks; Develop and improve analytical models, simulators, and data-analysis tools; Evaluate trade-offs in performance, scalability, utilization, capacity, and cost; Study hardware-software interactions and translate insights into architecture requirements; Develop and run targeted microbenchmarks on silicon; Compare analytical model predictions with measurements to improve accuracy; Communicate findings through data visualizations and technical reports.
Seniority
Senior, hands-on IC
