Multimodal AI Engineer: On-Device Inference for Games

Razer Inc.

Clermont-Dessous

Sur place

EUR 70 000 - 110 000

Plein temps

Il y a 13 jours

Générateur de candidature

Transformez ce poste en entretien — un CV et une lettre de motivation conçus selon ce que cet employeur recherche.

Passez les filtres ATS

Résumé du poste

Razer Inc. is seeking an AI engineer to design and optimize multimodal in-game event recognition systems. You will implement high-performance C++ modules for data acquisition, inference, and model serving, while collaborating with SDK developers for on-device optimization.

The role requires experience with OpenCV, PyTorch, or TensorFlow, and a strong background in computer vision or audio event classification, with a focus on low latency and scalable deployments across top games.

Qualifications

Proficient in C++ for high-performance implementation.
Solid understanding of ML fundamentals (CNNs, transformers, multimodal fusion).
Experience with OpenCV, PyTorch, or TensorFlow for model integration.
Background in computer vision or audio event classification.
Familiarity with dataset management, labeling, and augmentation techniques.
Experience with real-time inference and model compression for deployment.

Responsabilités

Designs and implements AI components for in-game event recognition, multimodal learning, and model optimization.
Develops CV and audio processing pipelines for automated dataset generation and labeling.
Collaborates on training workflows for top 100, 500, and 3000 games.
Builds the video decluttering pipeline to filter irrelevant gameplay segments.
Works with the Lead Engineer on model deployment optimization and SDK integration.
Implements and maintains C++ modules for data acquisition, inference, and model serving.
Focuses on performance tuning and inference latency reduction for on-device intelligence.