Senior C++ & GPU Engineer for On-Device ML

Abundant Code; Guildford; Hybrid; GBP 90,000 - 130,000; Full time

Job summary

Electronic Arts in Guildford, United Kingdom is seeking a Senior Software Engineer with deep expertise in C++ and GPU optimization to join our Machine Learning team. You will design end-to-end solutions for running ML models across devices and collaborate with game engineers and researchers to deploy models into EA's games.

The role focuses on speeding up inference on CPU and GPU, integrating ML into proprietary tools, and improving workflows for model import, testing, and analysis.

Qualifications

• At least 7+ years of hands-on C++ software engineering with multithreading and low-level optimisations.
• GPU programming experience and high-performance compute shader work in HLSL or equivalent.
• Strong debugging, profiling, and real-time software optimisation skills.
• Solid knowledge of software engineering fundamentals: version control, code reviews, automated tests, CI/CD, and Agile.

Responsibilities

• Design end-to-end solutions for running machine learning models on a variety of devices.
• Speed up inference on CPU and GPU so models run within performance targets and minimize impact on the core real-time game experience.
• Integrate ML solutions into our proprietary tools and game runtimes, and improve the workflows game teams use to import, test, and analyse their models.
• Collaborate with ML experts across EA to assess, apply, and optimize models and architectures for on-device performance.

Skills

C++

Multithreading

GPU programming

HLSL shader

Debugging

Profiling

CI/CD

Version control

Agile

Remote collaboration

Education

BSc or MSc in Computer Science, Engineering, Mathematics or equivalent

Tools

ONNX Runtime

PyTorch

TensorFlow

Job description

Electronic Arts in Guildford, United Kingdom is seeking a Senior Software Engineer with deep expertise in C++ and GPU optimization to join our Machine Learning team. You will design end-to-end solutions for running ML models across devices and collaborate with game engineers and researchers to deploy models into EA's games.

The role focuses on speeding up inference on CPU and GPU, integrating ML into proprietary tools, and improving workflows for model import, testing, and analysis.