Unverified50% confidenceOpinionExact time
据B站马士兵AI大模型公开课分析，当前大模型岗位要求能根据企业业务需求定制化开发智能体或RAG系统，工程化落地能力成为面试高频考点
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/25/2026
First Seen
Valid until: 10/23/2026
Sources
Related Claims
UnverifiedAn increasing number of real-world scenarios involve calling pre-trained large models, designing prompts, building RAG systems, and embedding models into products.73% similarUnverified将招聘SOP和岗位评估标准注入智能体长期记忆本质上是一种RAG（检索增强生成）工程实践72% similarUnverifiedMainstream industry approaches to personalized AI training include prompt-engineering-based personality description injection, RAG-based personal knowledge base referencing, and style transfer based on lightweight fine-tuning techniques such as LoRA.70% similarUnverified应用算法是在已有大模型基础上进行二次开发、微调、本地化部署和私有数据训练，侧重工程实践，典型技术包括LoRA、QLoRA等参数高效微调方法和RAG检索增强生成技术，一本本科基本能够得上69% similarUnverifiedThe training recipes published by SWE-bench cover key aspects including data preparation, model selection, fine-tuning strategies, and inference frameworks.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/613191API
curl https://kongchang.com/api/v1/knowledge/claims/613191MCP
get_claim(id=613191)