Senior AI Inference Engineer
Core
Develop and optimize GPU kernels for large model inference scenarios, focusing on core operators like GEMM, Attention, and MoE.
Role type
Senior IC GPU kernel engineer (LLM inference)
Builds
High-performance GPU kernels and automated optimization systems for large language models
Domain
AI / High-performance computing / GPU architecture
Deliverable
production ML models
Required skills
C/C++, Python, CUDA, Triton, HIP, CK, AITER, tiling, fusion, performance profiling
Preferred skills
LLM Coding Agent experience, CuteDSL, prior research in HPC or LLM inference optimization
