大模型平台研发工程师-国际化（北京/上海）
Core
Design and build a one-stop lifecycle management platform for large models, covering training, evaluation, version control, online deployment, and monitoring to improve R&D and O&M efficiency.
Role type
Senior IC platform engineering lead (LLM infrastructure)
Builds
A unified platform for model training, evaluation, deployment, and monitoring; a service gateway with resource scheduling; automated iteration workflows for risk control strategies.
Domain
Artificial Intelligence / Large Language Models / Distributed Systems
Deliverable
production ML models
Required skills
Distributed system architecture, data structures and algorithms, high-availability system design, Golang or Python, Prompt Engineering, RAG, Agent architecture, system observability, automated workflow design.
Preferred skills
LLM training and inference experience, Multi-Agent system construction, MCP or strategy platform experience, team leadership.
Responsibilities
Design and implement the full lifecycle management platform for large models; lead the construction of model service gateways and resource scheduling systems; design automated iteration workflows for model optimization; ensure high availability and scalability of the platform.
Seniority
Senior, hands-on IC