Principal AI Architect

Job Summary

Driving the future of AI infrastructure, the full-time Principal AI Performance Modeling Architect will lead performance modeling and optimization for large-scale ML systems, focusing on GPU architecture specifications to achieve significant performance gains in training and inference pipelines.

Key responsibilities:

• Lead performance modeling and optimization for multi-trillion parameter LLM training/inference across various modalities
• Architect memory-efficient training systems utilizing advanced techniques such as structured pruning and quantization
• Collaborate with internal and external stakeholders to disseminate results and iterate rapidly on innovative solutions

Required qualifications:

• Extensive experience optimizing large-scale ML systems and GPU architectures
• Deep expertise in CUDA programming and GPU memory hierarchies
• Proven track record in architecting distributed training systems for large-scale applications
• Expert knowledge of transformer architectures and model parallelism techniques
• Bachelor's, MS, or PhD in Computer Science/Engineering or equivalent industry experience