北京-AI Infra工程师(J100730)
Core
Design and optimize infrastructure for large model training and inference, including distributed training frameworks, inference engines, and model compression/deployment.
Role type
Senior IC AI Infrastructure Engineer
Builds
High-throughput, stable training and inference systems on heterogeneous hardware (GPU/NPU)
Domain
AI Infrastructure / High-Performance Computing
Deliverable
production ML models
Required skills
Distributed systems, Parallel computing, CUDA programming, C++, Python, Deep learning frameworks (PyTorch/PaddlePaddle), Model quantization, Inference optimization, Memory management, Operator fusion, XLA optimization
Preferred skills
Experience with mixed-precision training, KV Cache optimization, Heterogeneous hardware deployment
Sourced via baidu · Listed on CareerPlan, which tracks 844,000+ jobs from 20+ sources.
