视觉大模型推理部署工程师-智能创作（北京/上海/杭州/深圳）
Core
Design and implement architecture for visual large model (LLM/VLM/AIGC) inference services, optimize performance, and deploy applications to ensure high availability and low cost.
Role type
Senior IC machine-learning engineer (visual large model inference)
Builds
High-availability, low-cost inference services for visual large models
Domain
AI Engineering / Large Language Models / Visual Models
Deliverable
production ML models
Required skills
Python, Go, AI engineering architecture design, performance optimization, GPU/NPU hardware knowledge, distributed high-concurrency system architecture, ComfyUI, vLLM, SGLang, Ray
Preferred skills
Large-scale GPU cluster deployment optimization, extensive experience in large model service deployment
Responsibilities
Design and implement inference service architecture; Optimize inference performance; Deploy services and ensure application delivery; Collaborate with algorithm and product teams for high-standard delivery.