System Performance Engineer - AI/ML, Platform Architecture

Summary

Imagine what you can do here. At Apple, new ideas have a way of becoming extraordinary products very quickly. Bring passion and dedication to your job, and there’s no telling what we can accomplish together.

Do you love to spend your free time tinkering with new gadgets and exploring cutting-edge technologies? Do you obsess over every detail of product experience? Are you constantly looking out for the latest technology developments and tracking the shifting landscape?

We explore real user workflows and everyday use cases, measure them rigorously across hardware and software, and turn what we learn into insights that shape current and future products. As AI becomes central to the product experience, we’re looking for an engineer to work on our AI workload strategy end to end - from curating what we measure, to running it across devices, to presenting what it means.

Our team is collaborative, creative, and passionate about the value we add to future product designs. Join this team, and you’ll collaborate with engineers across Apple to deep dive into hardware and software technologies, uncover potential optimization opportunities to enhance and improve customer experiences across Apple devices. Come join us!

About the role

As a System Performance Engineer - AI/ML on the Platform Architecture team, you will play a critical role in ensuring the performance excellence of Apple products by benchmarking AI experiences.

Responsibilities

• Curate and define AI workloads that represent real user experiences across market segments, define useful metrics, design experiments to measure and analyze the experiences.
• Run workloads across diverse hardware and software, and build useful insights informed by data and heuristics.

Analyze system behavior and data to explain not just what the numbers are, but why - connecting observed performance to underlying hardware and software behavior, and uncovering optimization opportunities across all aspects of hardware (CPU, GPU, Neural Engine, memory, storage), software (OS, drivers, applications), and system characteristics (thermals, power, and acoustics).

• Present findings and provide insights to executive leadership and a broad network of cross-functional partners, translating deep technical analysis into clear, actionable narratives.
• Stay on top of the latest developments in AI technology - new models, frameworks, accelerators, device features, and product launches.

Minimum Qualifications

• Bachelor’s Degree in Computer Engineering, Electrical Engineering, Computer Science, or a related degree.
• Experience in performance measurement, analysis, debug, and optimization using software profiling tools (e.g. VTune, Nsight, uProf, WPA, HWInfo).
• Experience curating, running, and interpreting AI/ML workloads or benchmarks, and experience with the frameworks and hardware-specific runtimes used (e.g., PyTorch, TensorFlow, TensorRT/CUDA, OpenVINO).

Preferred Qualifications

• 3+ years of industry experience in performance analysis.
• Understanding of the hardware that accelerates AI/ML — GPUs, NPUs, and the memory and bandwidth factors that drive performance — and why they cause performance differences.
• Understanding of OS fundamentals and system-level performance, including performance, power, and thermal profiling tools.
• Good communication and presentation skills, with the ability to distill complex analysis for technical and executive audiences.
• Excellent interpersonal skills; ability to work cross-functionally from silicon to SW teams.
• Passion and desire to learn new things, from deep technical topics to user workflows.
• Proficiency in Python for scripting and automation.
• Knowledge of macOS, Windows, and Linux operating systems.