推理GPU性能优化专家 - Seed Model
Core
Develop and optimize company-level large model inference frameworks and build high-performance LLM inference engines using GPU and CUDA optimizations.
Role type
Senior IC machine-learning systems engineer (LLM inference)
Builds
High-performance LLM inference engines for company-wide large models
Domain
AI / Large Language Models / GPU Computing
Deliverable
production ML models
Required skills
C/C++, Python, GPU high-performance computing, CUDA, computer architecture, parallel computing, memory optimization, low-bit computation, deep learning frameworks, neural network operators
Preferred skills
TensorRT-LLM, ORCA, vLLM, algorithm-system joint optimization
Responsibilities
Develop and optimize company-level large model inference frameworks; Build high-performance LLM inference engines via GPU/CUDA optimization; Research and introduce forward-looking ML system technologies; Collaborate with algorithm teams for joint optimization
Seniority
Senior, hands-on IC
