深圳招聘

Job description

1. Research and develop state of art model compression techniques including model distillation, pruning, quantization, model binarization, and others for CNN, RNN, LSTM models.

2. Implementing novel deep neural network architectures and develop advanced training algorithm to support model structure training, auto pruning and low-bit quantization.

3. Apply and optimize model compression technique to variety of models in computer vision applications, audio applications, and others.

4. Research and optimize model compression technique for Kneron CNN accelerator and jointly optimize hardware architecture for compressed model.

Requirements

1. M.S./PhD in Computer Science, Machine Learning, Mathematics or similar field (Ph.D. is preferred)

2. 3+ years of industry/academia experience with deep learning algorithm development and optimization.

3. 3-5 years of software engineering experience in an academic or industrial setting.

4. Holistic understanding of deep learning concepts, state of the art in model compression research and the mathematics of machine learning.

5. Solid understanding of CNN, RNN, LSTM, variety of training method, learning rate choice, hyper-parameter tuning.

6. Research experience on any model compression technique including model distillation, pruning, post train quantization, quantization retrain, model binarization, and NAS.

7. Strong experience in C/C++ programing.

8. Hands-on experience in computer vision and deep learning frameworks, e.g., OpenCV, Tensorflow, Keras, Pytorch, and Caffe.

9. Experience on hardware architecture design is a plus.

10. Ability to quickly adapt to new situations, learn new technologies, and collaborate and communicate effectively.

11. Experience with parallel computing, GPU/CUDA, DSP, and OpenCL programming is a plus.

12. Top-tier conference publication records, including but not limited to CVPR, ICCV, ECCV, NIPS, ICML, is a strong plus.

耐能人工智能(Kneron Inc，)于2014年在美国圣地亚哥成立，目前在中国深圳与珠海、杭州皆已成立耐能人工智能公司，耐能Kneron本着以人工智能技术为人类提供智慧服务的使命，致力于为全球提供人工智能及深度学习的软硬件整体解决方案。
   耐能Kneron提出“云+AI+I2oT"（I2oT：Intelligent Internet of Things)的人工智能软硬件整体解决方案, 通过深度学习的人工智能，使得物联网变得更智能。当物联网上的每一个终端都具有人工智能的能力，我们能加速单个终端的执行能力，加大各个终端之间的互通能力，减轻云端的数据处理能力，从而使得物联网变得更智能。
耐能kneron官网：www.kneron.com