服务端AI架构负责人-剪映（深圳/广州）
Core
Design and build AI engineering architecture (including Agent architecture and AI gateways) and optimize GPU resource management for the Jianying product suite.
Role type
Senior AI Infrastructure Architect
Builds
AI engineering systems, GPU resource management platforms, and optimized inference frameworks for video editing tools.
Domain
Consumer media software / AI Infrastructure
Deliverable
production ML models
Required skills
Distributed system architecture, GPU resource management, AI/ML engineering deployment, complex system operations, multi-language backend development (Golang/C++/Python), inference acceleration frameworks
Preferred skills
Model engineering optimization, online training architecture, deep learning engineering
Technologies
Golang, C++, Python, Distributed systems, GPU management systems, Inference acceleration frameworks
Responsibilities
Design AI engineering architecture including Agent systems and AI gateways; Build and manage GPU resource systems across different infrastructure platforms; Optimize GPU utilization in collaboration with infrastructure teams; Implement industry inference acceleration frameworks and methods for key models.
Seniority
Senior, hands-on IC
