On Device ML Engineer : PyTorch Interoperability

Role Number : 200631247-0836

Summary

Imagine being at the forefront of an evolution where innovative AI meets the elegance of Apple silicon. The On-Device Machine Learning team transforms groundbreaking research into practical applications, enabling billions of Apple devices to run powerful AI models locally, privately, and efficiently. We stand at the unique intersection of research, software engineering, hardware engineering, and product development, making Apple the leading destination for machine learning innovation.

Our team builds the essential infrastructure that enables machine learning at scale on Apple devices. This involves onboarding innovative architectures to embedded systems, developing optimization toolkits for model compression and acceleration, building ML compilers and runtimes for efficient execution, and creating comprehensive benchmarking and debugging toolchains. This infrastructure forms the backbone of Apple’s machine learning workflows across Camera, Siri, Health, Vision, and other core experiences, contributing to the overall Apple Intelligence ecosystem.

If you are passionate about the technical challenges of running sophisticated ML models across all devices, from resource-constrained devices to powerful clusters, and eager to directly impact how machine learning operates across the Apple ecosystem, this role presents a great opportunity to work on the next generation of intelligent experiences on Apple platforms.

Our group is looking for an ML Infrastructure Engineer, with a focus on interoperability with PyTorch. The role entails working closely with model authoring and compiler teams to ensure that the latest PyTorch features are interoperable with our platform and proposing upstream changes to PyTorch in order to better support interoperability where needed.

Description

We’re building an end-to-end developer experience for machine learning development that employs Apple’s vertical integration. This allows developers to iterate on model authoring, optimization, transformation, execution, debugging, profiling, and analysis. This role focuses on the core runtime for execution across a wide variety of devices and use cases.

We’re seeking a highly motivated software engineer who is creative, versatile, and passionate about machine learning, common compiler optimizations, and system software engineering in the fast-paced and dynamic field of machine learning. Given the prevalence of PyTorch in the ML ecosystem, we support integrations and interoperability that allow for seamlessly switching between PyTorch and our platform’s tools in order to better train, optimize, and export models that run across all types of devices and device clusters.

Minimum Qualifications

3-5 years working on tooling built in Python 3

Familiarity with Torch Dynamo and downstream infrastructure (torch.export and torch.compile)

Familiarity with the core Aten and prims opsets and related infrastructure

Preferred Qualifications

Experience working on or adjacent to MLIR-based compilers.

Familiarity with QAT and other compression and quantization techniques employing PyTorch workflows

Familiarity with other training and inference frameworks including JAX, MLX, etc.

Familiarity with C++ and Swift

Familiarity with GPU programming paradigms

Apple is an equal opportunity employer that is committed to inclusion and diversity. We seek to promote equal opportunity for all applicants without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, Veteran status, or other legally protected characteristics. Learn more about your EEO rights as an applicant () .