Senior Staff AI Accelerator Performance Architect

What you'll do

• Build and validate analytical, simulation-based, or trace-driven performance models for accelerator architectures and workloads.
• Analyze workload performance, identify bottlenecks, and quantify opportunities and architectural feature returns.
• Collaborate with architecture, compiler, kernel, runtime, and systems teams; communicate recommendations for product and architecture decisions.

What they ask for

• 7+ years of experience in performance analysis, performance modeling, or architecture exploration for high-performance computing systems.
• Strong hardware architecture understanding and experience developing performance models using Python, C++ or similar environments.
• Solid understanding of processor architecture, memory systems, interconnects, parallel execution, and hardware resource constraints.
• MS or PhD in Electrical Engineering, Computer Engineering, Computer Science, or equivalent practical experience.

Nice to have

• Performance analysis of transformer inference or training workloads, including attention, GEMM/GEMV, collective communication, mixture-of-experts, quantization, or memory-constrained execution.
• Kernel/compiler/runtime optimization, distributed accelerator systems, model validation using RTL simulation, emulation, FPGA prototypes, or silicon measurements.

Pay

$175,000 to $275,000 USD annually, base salary

Tools

Python, C++, RTL, FPGA

AI focus

Analyze AI training and inference workloads and evaluate accelerator architecture performance and improvements.