Inference Performance Engineer : AI Speed & Scale

A leading AI hardware provider in Toronto seeks an engineer for the inference performance team. Candidates will work at the intersection of hardware and software, enhancing model inference speed. The role demands a strong background in computer architecture and requires a degree in Electrical Engineering or Computer Science. Ideal applicants should have at least 3 years of experience in relevant domains, including CPU / GPU performance and kernel optimization, along with proficiency in C++ and Python.

#J-18808-Ljbffr