Senior AI Engineer (On-Device AI)

Location: France

Company

Razer develops gaming products and technologies across gaming, biosensing, and peripheral applications.

What you will do

• Design, implement, and optimize AI/ML models for latency-sensitive on-device inference.
• Build real-time models that process biosignal and sensor data from peripherals and wearables.
• Optimize model performance and footprint through quantization, pruning, and acceleration for CPU, GPU, and NPU targets.
• Write production-quality C++ for SDK runtime and inference layers.
• Collaborate with platform, haptics, audio, and game-studio groups to expose AI capabilities through documented APIs.
• Profile and benchmark inference speed, memory usage, and energy efficiency.

Requirements

• 3+ years of experience in AI/ML engineering, applied machine learning, or a related role.
• Required proficiency in C++ and experience writing performant, maintainable code for real-time or systems contexts.
• Hands-on experience deploying machine learning models, preferably on-device or at the edge.
• Familiarity with ML frameworks and runtimes such as PyTorch, ONNX Runtime, TensorRT, llama.cpp, or GGML.
• Understanding of quantization, pruning, distillation, and their trade-offs.
• Strong performance-profiling skills and experience working within constrained compute and latency budgets.

Culture & Benefits

• Opportunity to contribute to products used by gamers globally.
• Collaboration within an approximately 25-person R&D team and across platform, haptics, and audio groups.
• Inclusive and respectful workplace committed to equal opportunity and reasonable accommodations.