- Development of AI compiler framework, high performance kernel authoring and acceleration onto next generation of hardware architectures.
- Contribute to the development of the industry-leading machine learning framework core compilers to support new state of the art inference and training machine learning/AI accelerators and optimize their performance.
- Collaborating with AI research scientists to accelerate the next generation of deep learning models such as recommendation systems, computer vision, or natural language processing.
- Develop core mathematical and system acceleration libraries and strategies to further accelerate AI workloads
- Analyze deep learning networks, estimate target latency and accuracy.
- Development of profiling tools for finding bottleneck parts of AI accelerators and models.
- Development of optimized inference application.