New: upload your resume and get matched to AI jobs. Free to start →

On-Device ML Compiler Engineer, Model Compilation

Cupertino, California, United States

Posted 17h ago

Job Location

Cupertino, California, United States

Tech Stack

Remote Work Policy

On-site

Categories

Machine Learning Engineer

About the job

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 better targeting the Apple Neural Engine.

We’re seeking a highly motivated software engineer who is creative, versatile, and passionate about machine learning, compiler, optimizations, and system software engineering in the fast-paced and dynamic field of machine learning. Our MLIR-based compiler stack targets the neural engine, GPU, and CPU in order to harness the full capabilities of the system for ML workflows and execution.

Responsibilities

Own core pieces of the MLIR-based compiler and runtime stack, with a focus on Apple Neural Engine support. Design and implement changes for a novel approach to target the Apple Neural Engine.

Expose compiler and runtime changes through our Python modules to enable new features for users. Connect the features to other Apple tracks, including agentic exploration, to optimize existing and new workflows

Work closely with hardware, software, and performance teams across the company to accelerate and optimize execution by taking advantage of the latest features in the hardware, OS, and drivers.

Propose upstream changes in MLIR to better support new features and workflows in the hardware that lead to more optimal execution performance across all types of devices and device clusters.

Minimum qualifications

3-5 years working on MLIR-based compilers.

Familiarity with common ML model architectures, execution schemes, and operations.

Familiarity with C++, Python

Familiarity with PyTorch

Preferred qualifications

Familiarity with Swift.

Familiarity with programming paradigms for the GPU, CPU, and Neural Engine.

Familiarity with writing kernels for ML model execution.