Senior LLM Integration Engineer

Drive model integration projects as a Senior Engineer focused on AI LLMs. Engage in end-to-end processes from architecture translation to runtime optimizations and performance debugging.

Be a vital member of the Inference Core Model Bringup team, responsible for the integration of advanced AI technologies on specialized systems. You will combine your expertise in deep learning frameworks with robust debugging skills to overcome complex challenges ensuring peak performance and efficiency. Your contributions will not only enhance the systems but also transform AI applications as a whole.

Key Responsibilities:

• Spearhead bringing ML models on Cerebras systems

• Enhance model architecture and runtime efficiencies

• Diagnose issues in compilers and hardware interactions

• Develop new tools and API enhancements for smoother workflows

Requirements:

• Bachelor’s, Master’s, or PhD in Computer Science or related

• Expertise in Python, C/C++, and various deep learning frameworks

• In-depth debugging capabilities focusing on performance

• Proven experience with LLVM/MLIR compiler technologies

• Strong grasp of optimization strategies for complex systems

Utilize your engineering skills to revolutionize the AI landscape through effective model integration and performance tuning strategies.