Description
Cerebras Systems is hiring an Inference Performance Engineer to improve the speed and throughput of model inference on its WSE hardware. The role combines low-level kernel and compiler optimization, runtime performance debugging, performance modeling, and development of visualization and diagnostic tools. Candidates need a degree in Electrical Engineering, Computer Science, or a related field, strong computer architecture knowledge, relevant 3+ years of experience, CPU/GPU simulator experience, performance profiling exposure, and comfort with C++ and Python.
