Full Stack LLM Engineer

Join the Inference Core Model Bringup team to rapidly deploy state-of-the-art open-source or customer-proprietary LLMs on Cerebras CSX systems. You’ll work end to end across model architecture translation, graph lowering, compiler optimizations, runtime integration, and performance tuning. The role focuses on debugging performance and correctness across model code, compiler IRs, runtime behavior, and hardware utilization, plus prototyping tool/API/automation improvements to accelerate bring-up.