We are seeking a skilled AI Engineer who are passionate about AI and optimization to join our team and contribute to the development of cutting-edge deep neural networks acceleration and compression framework.

Our works: Integral Neural Networks, Mixbit, Qsin.

Job Description

As an AI Engineer, you will be responsible for

Responsibilities

• Develop and implement optimization algorithms for deep neural networks and new accelerated model architectures
• Conduct testing of pipelines on public models
• Ensure the quality and accuracy of models
• Stay up-to-date with the latest trends and technologies in quantization, pruning, DNNs.
• Conduct experiments to verify your scientific hypotheses
• Write papers describing your new results
• Present your results at top-tier international conferences

Requirements

• Higher technical education with background in mathematics and algorithms
• Familiar with quantization and/or sparicification and/or pruning techniques for compression and acceleration of neural networks.
• Knowledge of linear algebra, functional analysis, and digital signal processing will be a nice bonus
• Knowledge in at least one of the following areas: Machine Learning, Computer Vision, Speech Recognition, Natural Language Processing
• Familiarity with DL framework PyTorch or Tensorflow
• Good programming skills in Python or C++ for implementing algorithms and conducting experiments
• Good written and spoken English