AI-Driven Systems Performance Architect

Apple Inc.; Cupertino (CA); On-site; USD 150,000 - 278,000; Full time

Benefits offered by this job

Stock programs

RSUs

Employee Stock Purchase Plan

Medical & dental coverage

Retirement benefits

Relocation

Job summary

Apple Inc. in Cupertino invites a Performance Architect to join the System Performance Architecture team.

You will characterize workloads, build high-level performance models, and guide next-generation SoCs to improve performance, power, and thermal efficiency. In this role you will dissect AI/ML workloads, develop traces and analysis tools, collaborate with OS, Compiler and ML software teams, and validate models against silicon measurements across pre- and post-silicon stages.

Qualifications

• Bachelor's degree in EE or Computer Engineering; 3+ years in computer architecture/performance analysis
• Understanding of CPU/GPU/NPU microarchitecture (pipelines, caches, etc.)
• Experience in performance analysis and modeling
• Expert in Python and C++ programming

Responsibilities

• Characterize workloads and analyze AI/ML workloads on Apple Silicon
• Develop high-level performance models to project future microarchitectures
• Create and guide workload traces and analysis tools to identify bottlenecks
• Collaborate with OS, Compiler, and ML teams to inform hardware trade-offs
• Validate performance models against silicon measurements across pre/post-silicon stages
• Assist with complex performance debugging on pre-silicon and post-silicon platforms

Skills

Python scripting

C++ coding

Performance analysis

Hardware modeling

Education

Bachelor's degree in EE or Computer Engineering

Master's degree preferred

Tools

Hardware performance counters

Profilers

GPU APIs (OpenGL/OpenCL/DirectX/Metal)

Job description

Apple Inc. in Cupertino invites a Performance Architect to join the System Performance Architecture team.

You will characterize workloads, build high-level performance models, and guide next-generation SoCs to improve performance, power, and thermal efficiency. In this role you will dissect AI/ML workloads, develop traces and analysis tools, collaborate with OS, Compiler and ML software teams, and validate models against silicon measurements across pre- and post-silicon stages.