On-device Machine Learning Infrastructure Engineer (Compiler & Runtime) Full-time

Summary
The On-Device Machine Learning team at Apple is responsible for the Research → Production of cutting edge machine learning models that power magical user experiences on Apple’s hardware and software platforms. Apple is the best place to do on-device machine learning, and this team sits at the heart of that discipline, interfacing with research, SW engineering, HW engineering, and products.

The team builds critical infrastructure that begins with onboarding the latest machine learning architectures to embedded devices, optimization toolkits to optimize these models to better suit the target devices, machine learning compilers and runtimes to execute these models as efficiently as possible, and the benchmarking, analysis and debugging toolchain needed to improve new model iterations. This infrastructure underpins most of Apple’s critical machine learning workflows across Camera, Siri, Health, Vision, etc., and as such is an integral part of Apple Intelligence.

Our group is looking for an ML Infrastructure Engineer, with a focus graph compilers and runtimes. The role entails building the world’s foremost ML graph compilation and runtime system capable of optimizing & executing ML models efficiently on Apple products and services.

Description
As an engineer in this role, you will be primarily focused on building graph compilers that optimize ML graphs coming from the most popular ML frameworks (PyTorch, JAX, MLX, etc.) to execute performantly and efficiently on Apple Silicon. The graph compiler and runtime provides out-of-the-box capability for executing ML models while also providing extensibility hooks for users to tailor specific goals. The role also has exposure to building higher level APIs and toolings to enable developers to visualize, diagnose, and debug correctness and performance issues while onboarding models to on-device deployment.

We are building the first end-to-end developer experience for ML development that, by taking advantage of Apple’s vertical integration, allows developers to iterate on model authoring, optimization, transformation, execution, debugging, profiling and analysis. The ML compiler is the backbone of such infrastructure stack.

The role requires understanding of ML operator primitives, common compiler optimizations (frontend/middle-end), runtimes, and system software engineering.

Key responsibilities:

* Define and build the on-device graph compiler, runtime, and kernels executing ML operators.
* Build production-critical system software for executing ML models on Apple Silicon.
* Optimize model execution for various system goals such as performance, energy efficiency, thermals, etc.