About the Role
We are looking for Deep Learning Compiler Engineers. In this role, you will be responsible for developing the tools used to compile state of the art deep learning models for custom Ceremorphic chips. You’ll collaborate with members of the deep learning software framework teams and the hardware architecture teams to accelerate the next generation of deep learning software. The scope of these efforts includes defining public APIs, performance tuning and analysis, crafting and implementing compiler and optimization techniques for neural networks, and other general software engineering work.
Key Requirements
- Excellent C/C++ programming and software design skills, including debugging, performance analysis, and test design.
- Experience working with high level machine learning frameworks (Tensorflow, PyTorch, MXNet)
- Knowledge of the machine learning hardware accelerator space (basic architectures, common techniques shared across the space, etc)
- Familiar with popular network architectures (ResNet, MobileNet, SSD, etc)
- Ability to work independently, define project goals and scope, and lead your own development effort
- Experience with the deep learning compiler space (ONNC, TVM, XLA, etc) is a huge plus
- Knowledge on OpenCL programming experience is preferable.
- Experience with the following technologies: deep learning models and algorithms, deep learning framework design, high performance compiler design.
