AI原生开发工程师
Core
Design AI-native architecture, manage LLM engineering, and ensure alignment with business goals.
Role type
Senior AI-native application engineer (LLM engineering)
Builds
AI-native applications, LLM engineering systems, and evaluation pipelines
Domain
Artificial Intelligence, Large Language Models, Distributed Systems
Deliverable
production ML models
Required skills
AI-native architecture design, Agent architecture, multi-agent collaboration, vector database design, LLM selection and optimization, distributed high-availability architecture, containerization (Docker, K8s), automated evaluation pipelines, cost and performance optimization
Preferred skills
Python, Go, TypeScript, Redis, Message Queues
Technologies
Qwen, LLaMA, DeepSeek, GLM, Docker, K8s, Redis, Vector Databases
Responsibilities
Design AI-native architecture and technical solutions, build LLM engineering architecture and performance/cost systems, conduct architecture reviews and technical decision-making, design and manage AI quantitative evaluation systems, optimize token consumption and inference latency, write technical documentation and lead architecture reviews
