AI性能优化专家-火山引擎
Core
Optimize performance of AI infrastructure and large model training/inference on heterogeneous cloud products, building universal software acceleration solutions.
Role type
Senior IC AI infrastructure performance engineer
Builds
General software acceleration solutions for AI workloads
Domain
Cloud computing, AI infrastructure, heterogeneous computing
Deliverable
production ML models
Required skills
Linux system programming, C/C++, Python, Go, distributed systems development, LLM/CV/NLP system principles, deep learning framework internals (TensorFlow/PyTorch), heterogeneous computing performance analysis, hardware-software co-optimization
Preferred skills
Cloud vendor AI Infra solutions knowledge, LLM training/inference optimization experience, model quantization and accuracy tuning, TensorRT/CUTLASS/Triton development, domestic AI accelerator ecosystem experience
