About the Role

In this role, you are responsible to build a highly scalable compiler toolchain for our future chip generations. You will participate in many fundamental architectural decisions and have the opportunity to contribute on upstream open-source projects.

What you will do:

• building/maintaining SEMRON's ML compiling toolchain for our accelerator
• design & implement various compiler operations as well as lowering and optimization passes
• collaborate with ML & quantization engineers/researchers to realize compilation of generic NNs for SEMRON's hardware

What you should bring in:

• in-depth knowledge of C++
• hands-on experience in compiler technologies like LLVM

Helpful but not required:

• experience with machine learning compiler infrastructure like MLIR/IREE or TVM
• experience in polyhedral compilation techniques

About us

SEMRON develops a 3D scaled AI inference chip, incorporating GPT-3.5-like models on a square cm silicon with minimal power consumption. This revolutionary CMOS-compatible semiconductor technology enables running generative AI at the edge, making it possible for wearable tech, smartphones, and beyond. With a trend towards large foundation models, SEMRON can serve multiple markets with minimal adjustments and simplify the software stack.