Accelerate AI innovation at Cerebras Systems as a Full Stack LLM Engineer. Contribute to cutting-edge model implementations on large-scale AI architecture in a fast-paced environment.

Cerebras Systems is seeking an experienced engineer for its Inference Core Model Bringup team. This role focuses on rapidly deploying state-of-the-art ML models on Cerebras CSX systems. Ideal candidates should be comfortable navigating the entire software stack, including debugging, performance tuning, and compiler optimizations.

Key Responsibilities: • Lead the bring-up of ML models on Cerebras CSX systems • Optimize model architectures, runtime integration, and performance • Debug issues across model code and runtime behavior • Prototype improvements for faster future bring-ups • Collaborate within a cross-functional engineering team

Requirements: • BS, MS, or PhD in Computer Science or Engineering • Expertise in Python, C/C++, and deep learning frameworks • Strong debugging s...