Job Description
1. Research and develop domain specific near data processing accelerator system software architecture and system solution for machine learning applications, in memory database applications, and data center/cloud computing applications.
2. Develop domain specific FPGA/ASIC PoC software modules, drivers, API etc.
3. Contribute system-level accelerator architecture definition including key features, performance requirements, block level definition.
4. Conduct AI system performance study, workloads characterization.
5. Identify opportunities in traditional computing applications and emerging AI applications; Help define new projects to address these opportunities and play a key technical role in their execution.
6. Documentation of architecture, design and IP specifications.
7. Create innovative IP, publish at conferences, and generate whitepapers.
Job requirements
1. M.S., or Ph.D. in Computer Architecture, Electrical Engineering, Computer Science or related field.
2. >5 years of experience and In-depth knowledge and experience of deep learning infrastructure (Torch, Caffe, TensorFlow, etc.), and neural network accelerator architecture with GPU/FPGA etc.
3. Deep understanding of GPU, FPGA, and ASIC etc. accelerator hardware and software architecture.
4. Proficiency in programing languages C/C++, Python etc., and ability to debug at system/kernel level.
5. Good knowledge and experience in large scale system software, operating system, and memory and storage system software etc.
6. Track record of innovation and creativity in problem solving.
7. Highly motivated with excellent verbal and written communication skills.
