Kernel Engineer (Internship and Full-time)

Highlights

• Design and optimize high-performance GPU kernels for training and inference.
• Co-design performance-aware models and infrastructure with ML researchers.
• Prototype and scale novel model architectures for frontier intelligence.

Ideal candidate

Strong algorithmic thinker with deep learning background who obsesses over hardware efficiency and loves co-designing with researchers to push GPU limits.

Requirements

• Experience in deep learning or related research areas
• Demonstrated exceptional capability in working on ML kernels
• Deep familiarity with PyTorch, Triton/TK/TileLang (>1 of), basic familiarity with CUDA, and knowledge of GPU architecture
• Clear and effective verbal and written communication
• Strong algorithmic thinker
• Able to learn quickly