About the position
Our team is seeking experienced iOS and macOS engineers to build the platform foundations that enable cutting-edge AI-driven products at Apple. This role focuses on native application development and operating system integration, working closely with ML research teams, hardware engineers, and design teams across the company. You'll be responsible for creating the iOS and macOS infrastructure that brings breakthrough AI technologies directly into users' hands through seamless, performant native experiences. Your work will establish the technical foundations that allow revolutionary ML capabilities to feel natural and effortless within Apple's ecosystem. In this role, you will architect and implement the native platform layer that bridges advanced ML models with iOS and macOS user experiences. You'll design high-performance native applications, create OS-level integrations for ML inference, implement system-level optimizations, and build the developer tools that enable AI features across Apple's platforms. The team values rapid iteration and real-world validation, bringing cutting-edge AI research into tangible user experiences that demonstrate the potential of next-generation computing. You'll collaborate with ML researchers, hardware teams, and product designers across Apple, translating breakthrough AI capabilities into polished native applications and system integrations. This unique opportunity positions you at the intersection of advanced AI research and world-class platform engineering, working on projects that define how users will interact with AI across Apple's ecosystem. You'll contribute to an environment that consistently pushes the boundaries of what's possible when sophisticated ML models meet beautifully crafted native experiences.
Responsibilities
- Design and build production-quality iOS and macOS applications that showcase and productize cutting-edge ML capabilities
- Implement deep OS-level integrations to optimize ML model inference, memory management, and power efficiency
- Create developer frameworks and APIs that enable AI features across Apple's app ecosystem
- Collaborate with ML teams to optimize model deployment and inference pipelines for Apple Silicon
- Build prototyping tools and infrastructure that accelerate AI research validation on native platforms
- Implement system-level performance optimizations for real-time AI workloads
- Partner with hardware teams to leverage specialized ML acceleration capabilities
- Create seamless user experiences that make complex AI capabilities feel intuitive and responsive
Requirements
- Deep expertise in Apple's ML frameworks including Core ML, Metal Performance Shaders, and Accelerate
- Experience with low-level optimization for Apple Silicon, including understanding of the Neural Engine and GPU architectures
- Knowledge of ML model formats, quantization techniques, and inference optimization strategies
- Experience building developer tools, frameworks, or SDKs used by other engineering teams
- Understanding of real-time systems, threading, and concurrent programming patterns
- Familiarity with AI/ML concepts and ability to collaborate effectively with ML researchers
- Experience with system-level iOS/macOS development including kernel extensions, background processing, or inter-process communication
- Track record of shipping innovative features that push the boundaries of what's possible on mobile and desktop platforms
- Strong problem-solving skills with experience debugging complex performance and integration issues
