On-Device ML Compiler Engineer

Apple Inc

Confirmed live yesterday High trust

Quick summary

Work type
On-site
Location
Cupertino, CA
Salary
$184,700–$324,800 / yr
Posted
8 days ago
Freshness
Confirmed live yesterday

Market check

Salary context

Above market

How this pay compares to similar roles

Similar $220k
This role $255k
$131k most similar roles pay here $346k

This role pays more than 85% of similar roles. Most pay $185,312–$254,750 — the shaded band above. At the midpoint, this role pays about $255k versus about $220k for comparable roles.

Based on 240 similar postings.

Employer

About Apple Inc

Apple Inc. is a multinational technology company known for designing and manufacturing consumer electronics, software, and online services, including the iPhone, Mac, iPad, and App Store. Industry: Consumer Electronics & Software

Apple Inc currently has 1984 open roles on FindRole.

Listed pay typically runs $175,000–$277,600 across 1590 roles with salary data.

Most-posted roles

View all roles at Apple Inc

At a glance

TL;DR · On-Device ML Compiler Engineer

On-Device ML Compiler Engineer, Model Compilation, Graphics, Games and Machine Learning joins the On-Device Machine Learning team to build essential infrastructure for running machine learning models locally across various Apple devices. The role focuses on model compilation within an MLIR-based compiler stack to target the neural engine, GPU, and CPU. You will be responsible for owning core pieces of the compiler stack that enable heterogeneous compute, proposing upstream changes in MLIR to support new features, and collaborating with hardware and performance teams to optimize execution across diverse hardware environments. The position requires expertise in C++, PyTorch or related training frameworks, and knowledge of common ML model architectures. Preferred skills include Swift, writing kernels for machine learning execution, and familiarity with programming paradigms specifically for the GPU, CPU, and Neural Engine.

What you'll do

  • Develop and optimize MLIR-based compiler stacks to target the Neural Engine, GPU, and CPU.
  • Propose upstream changes in MLIR to support new hardware features and improve execution performance.
  • Own core components of the compiler stack that enable heterogeneous compute across all Apple devices.
  • Optimize machine learning model execution for a range of hardware from resource-constrained watches to high-end Macs.
  • Collaborate with hardware, software, and performance teams to integrate latest OS and driver features.
  • Build infrastructure for model compression, acceleration, and efficient runtime execution.
  • Develop tools for debugging, profiling, and analyzing machine learning workflows across the Apple ecosystem.

What we're looking for

  • Experience of 3-5 years working on MLIR-based compilers.
  • Familiarity with C++.
  • Familiarity with PyTorch or related training frameworks.
  • Familiarity with common ML model architectures, execution schemes, and operations.
  • Familiarity with Swift.
  • Familiarity with programming paradigms for the GPU, CPU, and Neural Engine.
  • Familiarity with writing kernels for ML model execution.

More like this

Similar roles

On-Device ML Compiler Engineer

Apple Inc

Cupertino, CA 58 days ago $150,400$277,600
MLIR C++ PyTorch Swift GPU Neural Engine Compiler Optimization Machine Learning Model Compression System Software Profiling Debugging Benchmarking

Machine Learning Compiler Engineer

Apple Inc

Sunnyvale, CA 36 days ago $150,400$277,600
C++ LLVM MLIR Compiler Design Intermediate Representation JIT) compilation Neural Network Inference Multi-threading Program Analysis Register Allocation Code Generation Deep Learning Frameworks
3+ yrs exp

GPU ML Engineer

Apple Inc

Cupertino, CA 23 days ago $184,700$324,800
Metal Performance Shaders GPU Programming Machine Learning Linear Algebra Computer Vision Parallel Programming Computer Architecture Image Processing Numerical Methods
2+ yrs exp