AI/ML Silicon Performance Engineer

Apple Inc.; Cupertino (CA); Hybrid; USD 185,000 - 325,000; Full time

Benefits offered by this job

Stock options

Comprehensive medical and dental cover

Retirement benefits

Tuition reimbursement

Relocation assistance

Job summary

Apple Inc. in Cupertino, California, is seeking a performance-focused engineer to analyze workloads and identify bottlenecks in hardware and software.

You will benchmark, optimize, and propose improvements for Apple Silicon, including Neural Engine, GPU, and CPU workloads. The role involves collaborating with silicon and software teams to model performance and develop efficient, low-level libraries for AI/ML workloads, leveraging C/C++, Python, and PyTorch.

Qualifications

• Bachelor’s degree in Computer Engineering, Computer Science, or a related field.
• Experience in software development for AI/ML HW accelerators, GPUs, or similar.
• Experience with AI/ML, graphics, or HPC performance benchmarks and workloads.

Responsibilities

• Conduct performance studies to inform and validate architecture decisions.
• Create optimized implementations of machine learning workloads on Apple Silicon, including Neural Engine, GPU, and CPU.
• Collaborate with system teams to create performance models of emerging AI/ML techniques and analyze system architecture trade-offs.
• Work with software development tools teams to deliver performance analysis instruments and optimized libraries and frameworks for AI/ML applications.

Skills

C/C++

Python

Performance benchmarks

Collaboration

Education

Bachelor’s degree in Computer Engineering/CS

MS/PhD preferred

Tools

PyTorch

CUDA

Job description

Apple Inc. in Cupertino, California, is seeking a performance-focused engineer to analyze workloads and identify bottlenecks in hardware and software.

You will benchmark, optimize, and propose improvements for Apple Silicon, including Neural Engine, GPU, and CPU workloads. The role involves collaborating with silicon and software teams to model performance and develop efficient, low-level libraries for AI/ML workloads, leveraging C/C++, Python, and PyTorch.