On-Device AI Systems Engineer

Apple Inc.; Cupertino, Northern (CA, KY); Hybrid; USD 150,000 - 278,000; Full time

Benefits offered by this job

Medical and dental coverage

Retirement benefits

Discounted products and services

Education expense reimbursement

Discretionary bonuses or commissions

Relocation

Job summary

Apple Inc. in Cupertino, California, is seeking a software engineer to own the development of daemons and frameworks powering on-device intelligence across iOS, macOS, and other Apple platforms.

You will work alongside ML and app engineers to manage model inference, routing to private cloud compute, and scheduling document processing for search while ensuring performance in resource-constrained environments.

Qualifications

• Expert-level proficiency in C/Objective-C/Swift.
• Knowledge of operating system architecture and systems programming fundamentals.
• Experience developing daemons, libraries, or CLI tools on Unix/Linux.
• Familiarity with machine learning concepts.
• Strong analytical and debugging skills.

Responsibilities

• Design, develop, and maintain daemons and frameworks that support on-device intelligence features across Apple platforms.
• Manage models for on-device inference and coordinate routing to private cloud compute.
• Schedule and optimize document processing workloads to power search experiences.
• Develop and improve unit tests and performance tests; diagnose and resolve customer-reported issues.
• Provide design guidance and technical expertise to partner engineering teams across the company.

Skills

C

Objective-C

Swift

OS architecture

Systems programming

Unix/Linux tools

ML concepts

Analytical debugging

Job description

Apple Inc. in Cupertino, California, is seeking a software engineer to own the development of daemons and frameworks powering on-device intelligence across iOS, macOS, and other Apple platforms.

You will work alongside ML and app engineers to manage model inference, routing to private cloud compute, and scheduling document processing for search while ensuring performance in resource-constrained environments.