AI服务端架构师-剪映CapCut（广州/深圳）
Core
Engineering deployment and inference optimization for key AI models in the Jianying/CapCut product suite, including building GPU resource management systems.
Role type
Senior AI Infrastructure Engineer (GPU & Model Serving)
Builds
Scalable AI inference services and GPU management infrastructure for video editing products
Domain
Consumer Media / AI Infrastructure
Deliverable
production ML models
Required skills
C++, Golang, concurrent programming, large-scale server architecture, data structures and algorithms
Preferred skills
PyTorch, TensorFlow, AIGC model training/inference optimization, TensorRT-LLM, vLLM
Technologies
TensorRT-LLM, vLLM, PyTorch, TensorFlow
Responsibilities
Deploy and optimize AI model inference; Build and manage GPU resource allocation across infrastructure platforms; Collaborate with infrastructure teams to improve GPU utilization.
Seniority
Senior, hands-on IC
