Machine Learning System Software Engineer

Apple Inc

Confirmed live 2 days ago High trust

Quick summary

Work type: On-site
Location: Sunnyvale, CA
Salary: $184,700–$324,800 / yr
Posted: 29 days ago
Freshness: Confirmed live 2 days ago
Nearby: 99+ roles within 25 mi

Market check

Salary context

Above market

How this pay compares to similar roles

Similar $223k

This role $255k

$157k most similar roles pay here $343k

This role pays more than 84% of similar roles. Most pay $192,050–$254,750 — the shaded band above. At the midpoint, this role pays about $255k versus about $223k 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 · Machine Learning System Software Engineer

Role Posting Log in to save

As a Machine Learning System Software Engineer on the Apple Neural Engine team, you will design and implement APIs for loading, compiling, scheduling, and executing models on device. You will architect systems for model lifecycle management, memory allocation strategies, and multi-model scheduling to ensure runtimes scale with hardware capabilities. Your daily work involves collaborating with driver, firmware, and compiler teams to co-design the runtime-to-silicon interface while profiling and optimizing end-to-end inference paths. The role requires deep proficiency in C and C++, knowledge of runtime systems like memory management and IPC, and experience with software-hardware interfaces such as DMA and command queues. You will address technical challenges regarding neural network inference, including operator execution and tensor memory layout, to deliver high-performance, low-power AI solutions across the product ecosystem using technologies like Metal or Vulkan compute.

Skills

C C++ Swift Rust Metal Vulkan TensorRT ONNX Runtime XLA Machine Learning Inference Engines Graph IR IPC RPC DMA Memory Management System Software Firmware

What you'll do

Design and implement APIs for the Neural Engine to manage model loading, compilation, scheduling, and execution.
Architect APIs for memory allocation strategies, multi-model scheduling, and concurrent execution across hardware capabilities.
Co-design the runtime-to-silicon interface with driver, firmware, and compiler teams to expose new hardware features.
Profile and optimize end-to-end inference paths by identifying bottlenecks in scheduling and compilation.
Support clients in adopting APIs and ensuring efficient integration of machine learning models.
Manage multi-client runtime scenarios including hardware access arbitration, priority management, and crash recovery.
Develop high-performance, low-power AI solutions for Apple products like Vision Pro, iPhone, and Mac.

What we're looking for

Bachelor of Science degree and at least 10 years of relevant industry experience.
Deep proficiency in C and C++ within large, production system software environments.
Experience shipping production system software and defining interfaces for other teams or external developers.
Understanding of runtime systems including process/thread models, memory management, IPC/RPC, and resource lifecycle.
Understanding of software-hardware interfaces such as registers, DMA, command queues, or similar accelerator interaction patterns.
Experience building or extending ML runtimes, inference engines, or accelerator driver stacks (preferred).
Familiarity with Swift, Rust, or other memory-safe systems languages (preferred).
Knowledge of ML model compilation pipelines, neural network inference, and multi-client runtime scenarios (preferred).

Save