GPU Software Architecture Engineer, Graphics, Games, & ML

Apple Inc

Quick summary

Work type
On-site
Location
Cupertino, CA
Salary
$181,100–$318,400 / yr
Posted
56 days ago

Market check

Salary context

Above market

How this pay compares to similar roles

Similar $211k
This role $250k
$143k most similar roles pay here $337k

This role pays more than 87% of similar roles. Most pay $184,150–$236,900 — the shaded band above. At the midpoint, this role pays about $250k versus about $211k 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 1723 open roles on FindRole.

Listed pay typically runs $162,500–$272,100 across 1398 roles with salary data.

Most-posted roles

View all roles at Apple Inc

At a glance

TL;DR · GPU Software Architecture Engineer, Graphics, Games, & ML

As a senior/principal GPU Software Architecture Engineer on Apple’s Silicon GPU SW architecture team within the Media, Graphics & Compute Technologies group, you will lead initiatives to accelerate server-side machine learning and multi-node distribution. Your daily work involves architecting next-generation distributed ML infrastructure by designing sophisticated parallelization strategies for large language model inference across server clusters, optimizing memory access patterns, and high-level distributed algorithms to maximize hardware utilization while minimizing latency. You’ll collaborate closely with silicon architects to influence future GPU designs based on your expertise in inference workload characteristics, and you will also build production systems that handle billions of requests daily. This role requires extensive experience in GPU programming (CUDA, ROCm), inter-node communication technologies like InfiniBand and RDMA, system programming in C/C++, and a deep understanding of distributed systems and parallel computing architectures, alongside proficiency with tensor frameworks such as PyTorch and TensorFlow.

What you'll do

  • Design and implement tensor/data/expert parallelism strategies for distributed server clusters.
  • Drive hardware and software roadmap decisions for ML acceleration initiatives.
  • Develop architectures achieving peak compute utilizations and optimal memory throughput.
  • Optimize distributed inference systems focusing on latency, throughput, and resource efficiency.
  • Architect scalable ML serving infrastructure with dynamic model sharding and fault tolerance.
  • Lead performance analysis and optimization of ML workloads across compute, memory, and network.
  • Drive adoption of advanced parallelization techniques like pipeline and expert parallelism.

What we're looking for

  • 10+ years of GPU programming experience with CUDA and ROCm
  • Expertise in high-performance computing and optimizing large-scale parallel workloads
  • Strong knowledge of inter-node communication technologies like InfiniBand and RDMA
  • Deep understanding of distributed systems, tensor frameworks, and parallel computing architectures
  • Excellent system programming skills in C/C++ required
  • Bachelor's degree in Computer Science or related technical field necessary

More like this

Similar roles

GPU Compiler Engineer, Graphics, Game and ML

Apple Inc

Cupertino, CA 36 days ago $126,800$190,900
Metal CUDA OpenGL OpenCL DirectX PyTorch Python C++ LLVM GCC CI/CD Git Linux macOS GPU Compiler IR TypeSystems MemoryHierarchy ComputerArchitecture

Principal Engineer, GPU Architect & Modeling

Samsung Electronics

Remote (3655 N 1St St, San Jose, Ca, Usa, US) 24 days ago $221,700$364,800
GPU Graphics Architecture PPA Optimization GPU Modeling Methodologies Performance Simulation Microarchitectural Analysis Ray Tracing AI/ML Acceleration Shader Architecture Texture Architecture Cross-Functional Collaboration Technical Leadership GPU Programming Models
Remote

System Software Engineer, GPU Development Tools

Nvidia

Santa Clara, CA +1 57 days ago $152,000$241,500
C++ Python CUDA DX OpenGL Vulkan Object-Oriented_Design_Patterns Chip_Simulation System_Simulation Virtual_Machines Containers Distributed_Programming
Hybrid

GPU Software Engineer

Qualcomm

San Diego, CA +1 25 days ago $98,900$148,300
C C++ Python Perl GPU APIs pre-silicon tests post-silicon tests design documentation team collaboration graphics programming