AI/ML Performance Engineer for SoC

Apple, Inc.; Seattle (WA); Presencial; USD 175.000 - 309.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Medical and dental coverage

Retirement benefits

Employee stock programs

Relocation assistance

Descripción de la vacante

Apple seeks a senior performance engineer in Seattle to analyze workloads, identify bottlenecks, and drive optimizations across Apple Silicon. You will develop high-performance ML implementations for Neural Engine, GPU, and CPU, and collaborate with silicon and software teams to shape system architecture.

You will prototype and benchmark algorithms, leverage PyTorch and profiling tools, and contribute to performance models and efficient algorithms while engaging with cross-functional partners.

Formación

• Bachelor’s degree or equivalent in Computer Engineering, Computer Science, or related field.
• 10+ years of relevant experience in software performance optimization and analysis.
• Proficiency in C/C++ and scripting; experience with AI/ML workloads and hardware accelerators.

Responsabilidades

• Conduct performance studies to inform architecture decisions.
• Create optimized implementations of ML workloads on Apple Silicon (Neural Engine, GPU, CPU).
• Collaborate with system teams to model performance and analyze trade-offs.
• Work with software tools teams to deliver performance analysis instruments and optimized libraries.

Conocimientos

C/C++ programming

Python scripting

AI/ML performance

GPU/Neural Engine

Computer architecture

Performance benchmarking

Educación

Bachelor’s degree in CS/CE

MS/PhD in related field

Herramientas

PyTorch

GPU profiling tools

Descripción del empleo

Apple seeks a senior performance engineer in Seattle to analyze workloads, identify bottlenecks, and drive optimizations across Apple Silicon. You will develop high-performance ML implementations for Neural Engine, GPU, and CPU, and collaborate with silicon and software teams to shape system architecture.

You will prototype and benchmark algorithms, leverage PyTorch and profiling tools, and contribute to performance models and efficient algorithms while engaging with cross-functional partners.