Senior Research Scientist/Engineer- Audio-visual speech enhancement
OPPO US Research Center
Palo Alto, California
Expiry Date :
Wed, 23 Jun 2021 23:59:59 GMT
Apply Job :
We live in a mobile and device driven world, where Deep Learning technology enables a new class of applications. This position aims to build an audio-visual speech enhancement system and to improve the video phone call quality. You will focus on designing/building a deep learning system with multimodal fusion/recognition/tracking modules for a high-tech product.
Duties and responsibilities
As a Senior Research Scientist/Engineer, you will be responsible for developing, improving, and optimizing an audio-visual speech enhancement system, including state-of-art neural network modules, and collaborating with engineer team for cloud/devices product delivering.
Seek scientific solutions to highly ambiguous problems by crafting a technical vision and building consensus across teams
Design, develop the audio-visual related system and deep learning models, with data processing, training and optimizing
Compress, quantize, and prune the models for mobile/cloud deployment.
PhD degree or MS degree with 3~5 years of professional experience in Computer Science, Electrical Engineering, Statics, Mathematics or equivalent.
Proficient knowledge of and experience with AI systems.
Track record of developing demanding deep learning algorithms and applications.
Experience in developing deep learning algorithms including multimodal fusion/recognition, etc.
Experience with one or more deep learning frameworks such as TensorFlow, PyTorch, Keras, Caffe, and MXNet.
Strong programming skills in Python, C/C++, Java, etc.
Experience in deploying deep learning algorithms and signal processing background.
Experience in quantization/acceleration for deep learning models.
Strong background in smartphone architecture or backend architecture.
Publications in top tier international conferences and journals, such as CVPR/ECCV/ICCV/NeurIPS/ICLR/PAMI/IJCV, etc.