Cerebras Systems Full Stack LLM Engineer

Become a pivotal part of Cerebras Systems as a Full Stack LLM Engineer. Focus on optimizing the performance of large language models on innovative wafer-scale AI architecture.

The Inference Core Model Bringup team needs an experienced engineer who excels in fast-paced environments to support large-scale ML applications. Your expertise will span from model architecture adjustment to runtime integration, ensuring incredible performance and effective debugging across the entire Cerebras software stack.

Key Responsibilities:

• Lead the bring up of ML models on Cerebras CSX systems

• Conduct performance tuning and optimization across the AI toolchain

• Identify and debug issues in model codes, IRs, and hardware utilization

• Propose enhancements for better automation in model deployments

Requirements:

• Bachelor's, Master's, or PhD in Computer Science or related discipline

• Strong familiarity with deep learning frameworks such as Tensor Flow

• Proven skills in performance profiling and debugging

• Experience with LLVM or MLIR compiler technologies

• Comfort with high-level coding in C/C++ and optimizations

Drive the future of AI application performance through your expert contributions at Cerebras Systems.
#J-18808-Ljbffr