The point where experts and best companies meet
Apple On-device ML Infrastructure Engineer Execution United States, California, Cupertino 938426336
21.04.2025
Share
In this role you will be providing technical guidance across our ML Execution stack, out side the boundaries of your own team: ensuring infrastructure, tooling and APIs for model compilation performance analysis and inference execution support all client needs and use cases from a common general workflow to highly flexible and specialized ones.- Identify, prioritize, design and implement solutions to address developer pain points, feature requests and feedback- Provide technical direction and implementations that ensure scalability, reliability, and maintainability of Core ML
- Bachelors in Computer Science, Engineering, or related discipline.
- Highly proficient in one or more programming languages (e.g., C++, Swift, Python) and experience with various development frameworks and tools.
- Deep understanding of system design, architecture patterns, and scalability concerns to build efficient, maintainable, and reliable software.
- Sound understanding of ML fundamentals and workflows involved in model deployment in production
- Knowledgable of ML workflow, runtime and app integration pain points and existing solutions in this space.
- Experience with any on-device ML stack, such as TFLite, ONNX, ExecuTorch, etc.
- Experience with open source machine learning models (Mistral, Phi, Gemma, Huggingface, etc)
- Experience with any compiler stack (MLIR/LLVM/TVM/...).
- Experience with any ML authoring framework (PyTorch, TensorFlow, JAX, etc.).
- Good communication skills, including ability to communicate with cross-functional audiences.
- Experience with machine learning accelerators and GPU programming.
Note: Apple benefit, compensation and employee stock programs are subject to eligibility requirements and other terms of the applicable plan or program.
These jobs might be a good fit
