About the Role

In this role you are responsible for integrating our custom accelerators with a wide range of embedded systems. You will work together with the compiler and application/ML team to define and implement the interface between our hardware and target systems.

What you will do:

• help the hardware/architecture team with defining the system architecture through virtual prototypes for next generation products
• develop bare metal RISC-V code to interface the automatically generated binaries with the host system
• develop code running on the host system (Linux, various RTOSes) connecting our accelerator to the application software
• help the compiler team by providing them primitives and hand written minimal examples for the compiler

What you should bring in:

• willingness to learn new technologies and tools, and apply them quickly
• thorough knowledge of C and C++
• experience in working with custom/basic tool chains (outside of ready-made IDEs)
• a good understanding of the basic technologies used in embedded systems
• basic knowledge of Linux/POSIX, and bare metal development

Helpful but not required:

• knowledge/enthusiasm for other programming languages
• python for auxiliary tasks
• other languages suited for embedded development, e.g. rust (we’re not married to C, C++)
• scala, verilog, systemverilog for working cloesely with the hardware design team
• experience in driver development for Linux and/or other RTOSes
• experience in working with custom systems, e.g. FPGA-SOCs

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.