Requirements

• 7+ years of hands-on software engineering experience with C++, including expertise in multithreading and low-level/near-hardware optimizations.
• GPU programming experience, including writing high-performance compute shaders in HLSL (or equivalent).
• Proficient in debugging, profiling, and optimizing real-time software.
• Understand and practice software engineering fundamentals such as version control, code reviews, documentation, automated testing, coding standards, CI/CD, issue tracking, and Agile methodologies.
• Experience collaborating and sharing updates with developers and partners, including remote and asynchronous teams across different time zones.
• BSc or MSc degree in Computer Science, Engineering, Mathematics, or equivalent professional experience.

Nice to have

• Experience with machine learning inference runtimes or engines such as ONNX Runtime, llama.cpp, or similar technologies.
• Familiarity with PyTorch, TensorFlow or other similar frameworks.
• Experience owning technical projects end to end and mentoring other engineers.

What you'll be doing

• 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 proprietary tools and game runtimes, and improve workflows for game teams to import, test, and analyze their models.
• Collaborate with ML experts across EA to assess, apply, and optimize models and architectures for on-device performance.