ML Runtime Engineer for On-Device Gaming

Global Sports Jobs Limited; Guildford; On-site; GBP 70,000 - 100,000; Full time

Job summary

Electronic Arts in the UK is seeking a Software Engineer to develop and integrate runtime machine learning solutions for on-device gameplay. You will work with engine development leaders, game teams, and researchers to deploy ML models inside Frostbite-enabled EA games.

The role requires 5+ years of C++ software engineering, GPU programming, and hands-on ML experience with frameworks like PyTorch or TensorFlow. You will contribute to end-to-end ML systems and advance on-device performance.

Qualifications

• 5+ years hands-on software engineering with C++ and multithreading.
• Experience profiling and optimizing real-time software.
• Experience with ML frameworks PyTorch or TensorFlow.
• Experience shipping end-to-end ML systems in production environments.
• Knowledge of GPU programming and ONNX or similar representations.

Responsibilities

• Evaluate, adapt, extend, and improve ML runtime technologies.
• Collaborate with ML experts to scale models for on-device performance.
• Translate ML tradeoffs and constraints for diverse audiences.
• Build end-to-end ML models across multiple devices.
• Write clean, well-documented, well-tested code that fits existing systems.
• Stay updated on Deep Learning, RL, Generative AI developments.
• Contribute to EA ML/AI communities and mentor teammates.

Skills

C++

Multithreading

Performance optimization

Profiling

CI/CD

Agile development

PyTorch

TensorFlow

ONNX

GPU programming

Game programming

End-to-end ML systems

Education

BSc/MSc in CS/Engineering/Math

Tools

Git

CI/CD pipelines

Code reviews

Job description

Electronic Arts in the UK is seeking a Software Engineer to develop and integrate runtime machine learning solutions for on-device gameplay. You will work with engine development leaders, game teams, and researchers to deploy ML models inside Frostbite-enabled EA games.

The role requires 5+ years of C++ software engineering, GPU programming, and hands-on ML experience with frameworks like PyTorch or TensorFlow. You will contribute to end-to-end ML systems and advance on-device performance.