An independent AI consultant developed a three-tier system for a 400-employee precision parts manufacturer near Osaka to address the impending retirement of two veteran inspectors with 99.7% accuracy. First, 60 hours of inspectors' verbal explanations were recorded and transcribed using LLMs to build a retrievable knowledge base of tacit diagnostic logic. A RAG system enables new inspectors to query similar cases, while a vision AI model classifies defects with root cause suggestions. After five months, A/B testing showed AI-assisted new inspectors reached 99.2% accuracy, up from 96%, and the knowledge base was adopted by production engineers. The project reframed the initial request from a simple AI visual inspection to a knowledge preservation system.
Livid demonstrated that by creating a custom node like /go/wunder on V2EX and posting detailed product feature descriptions there, V2EX Chat can answer product-related questions using those posts as context. The example uses a specific edge.v2ex.com chat session link to show the AI replying solely based on node content. This effectively turns V2EX Chat into a retrieval-augmented knowledge base, enabling product Q&A without building a separate chatbot.
A well-known game company in Beijing (near Anzhenmen) has posted urgent openings for three AI engineering roles: AI Development Senior Engineer (30k-60k RMB), Agent Development Engineer (30k-50k RMB), and Algorithm Engineer (45k-65k RMB). The positions involve building AI-powered workflows and agent systems for game AB testing and commercial optimization, integrating large language models, and deploying RAG pipelines with LangChain. Key responsibilities include automating experiment design, optimizing ad bidding and recommendation algorithms, and supporting cross-team data engineering. Required skills span Python, PyTorch, LangChain, distributed systems, and familiarity with both closed-source and open-source LLMs (GPT-4o, Llama 3, Qwen, Mistral). The company offers standard benefits including weekends off, social insurance, free meals, and housing allowance.
A leading FinTech platform in Hangzhou is seeking an AI CTO with a monthly salary up to 150k plus stock options. The role involves building a financial AI Agent from scratch, including intent recognition, long-chain reasoning, memory mechanisms, and RAG with knowledge graphs. The ideal candidate has 8+ years of experience, has led teams of 5+, and has delivered 0-to-1 AI products. The CEO, a serial entrepreneur and angel investor, values entrepreneurial spirit and may become an investor in your future startup. This is a rare opportunity to work with a potential mentor while building cutting-edge AI in finance.