Machine Learning Systems Engineer, Siri Runtime Systems and Interaction

Apple Apple · Big Tech · Cupertino, CA · Software and Services

Machine Learning Systems Engineer for Siri at Apple, focusing on integrating, optimizing, and deploying ML models into production software pipelines for resource-constrained platforms. The role involves building infrastructure for ML evaluation and analysis, collaborating with ML engineers, and ensuring performance and reliability of ML workloads within the Siri ecosystem.

What you'd actually do

  1. Integrating ML models into production software pipelines with focus on performance and reliability
  2. Building and optimizing infrastructure for ML model evaluation, analysis, and deployment
  3. Collaborating with ML engineers to understand model requirements and translate them into efficient system implementations
  4. Optimization of existing systems for ML workloads and debugging complex software-ML integration issues
  5. Working cross-functionally to drive requirements from concept through feature launch

Skills

Required

  • Swift
  • C++
  • Objective-C
  • Machine learning concepts
  • Model inference
  • ML system design principles
  • Algorithm optimization
  • Resource-constrained platforms

Nice to have

  • Production-quality software development
  • ML infrastructure
  • Evaluation pipelines
  • Training systems
  • Core ML
  • PyTorch
  • TensorFlow
  • Model optimization techniques

What the JD emphasized

  • 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

Other signals

  • integrating ML models into production software pipelines
  • optimizing infrastructure for ML model evaluation, analysis, and deployment
  • optimization of existing systems for ML workloads
  • ML system design principles
  • resource-constrained platforms