AI/ML Platform Performance Engineer | Equity Benefits

Apple, Inc.; Santa Clara (CA); On-site; USD 150,000 - 225,000; Full time

Benefits offered by this job

Employee stock programs

Relocation assistance

Educational expense reimbursement

Job summary

Apple, Inc. in Santa Clara, California is seeking a System Performance Engineer - AI/ML for the Platform Architecture team.

You will benchmark AI experiences, curate workloads, define metrics, and design experiments spanning hardware and software to ensure performance excellence across devices. You will analyze system behavior, tie performance to CPU/GPU/Neural Engine, and present actionable insights to leadership.

Qualifications

• Bachelor’s degree in a related field.
• Experience with performance measurement, analysis, debugging and optimization tools.
• Experience curating, running and interpreting AI/ML workloads or benchmarks with relevant runtimes.

Responsibilities

• Curate and define AI workloads representing real user experiences; define metrics and design experiments.
• Run workloads across diverse hardware and software; build insights from data and heuristics.
• Analyze system behavior to connect performance to hardware/software and identify optimization opportunities.
• Present findings to executive leadership and cross-functional partners with clear narratives.
• Stay updated on AI tech: models, frameworks, accelerators, device features, and launches.

Skills

Python scripting

Performance analysis

Cross-functional collaboration

OS & hardware profiling

Education

Bachelor's Degree in Computer Engineering, Electrical Engineering, or Computer Science

Tools

VTune

Nsight

uProf

WPA

HWInfo

PyTorch

TensorFlow

TensorRT/CUDA

OpenVINO

Job description

Apple, Inc. in Santa Clara, California is seeking a System Performance Engineer - AI/ML for the Platform Architecture team.

You will benchmark AI experiences, curate workloads, define metrics, and design experiments spanning hardware and software to ensure performance excellence across devices. You will analyze system behavior, tie performance to CPU/GPU/Neural Engine, and present actionable insights to leadership.