Machine Learning Systems Engineer, Siri Runtime Systems and Interaction

Summary

The Siri Team at Apple is actively looking for a highly motivated Systems Software Engineer to contribute to and build Apple's future technologies that power delightful Siri experiences supercharged with Apple Intelligence. The successful candidate will be a skilled software engineer with strong ML fundamentals who enjoys problem-solving and is comfortable with designing, building, and optimizing system software that integrates machine learning capabilities.

Our team builds high-quality software that powers delightful Siri-based experiences in the Apple ecosystem. We value passion for excellence and a deep commitment to building high-quality software. If you want to impact millions of customers around the world by working on the most advanced technology solutions, we want to talk to you.

Description

As a Machine Learning Systems Engineer in the Siri Group at Apple, you will work at the intersection of software engineering and machine learning, partnering with cross-functional teams to solve high-impact problems on Apple products.

Responsibilities

• Integrating ML models into production software pipelines with focus on performance and reliability
• Building and optimizing infrastructure for ML model evaluation, analysis, and deployment 
Collaborating with ML engineers to understand model requirements and translate them into efficient system implementations
• Optimization of existing systems for ML workloads and debugging complex software-ML integration issues
• Working cross-functionally to drive requirements from concept through feature launch
• Writing clean, maintainable production code with comprehensive documentation and tests
• Contributing to architecture decisions, design reviews, and peer code reviews
• Acting as a force-multiplier by enabling both engineering and ML team members to be more productive

Minimum Qualifications

• Strong programming skills in Swift / C++ / Objective-C
• Solid understanding of machine learning concepts, model inference, and ML system design principles
• Experience developing and optimizing algorithms that run efficiently on resource-constrained platforms
• Passionate about delivering high-quality products, comfortable with ambiguity, intellectually curious and driven to find creative solutions
• Ability to thrive in collaborative environments with multiple cross-functional teams and communicate clearly with both engineering and ML teams
• BS (or higher) in Computer Science, Machine Learning, or related disciplines

Preferred Qualifications

• Demonstrated experience building production-quality software
• Experience building ML infrastructure, evaluation pipelines, or training systems
• Familiarity with ML frameworks (Core ML, PyTorch, TensorFlow) and model optimization techniques