任職要求 / Qualifications 經(jīng)驗:5–8 年軟件/數(shù)據(jù)/ML 經(jīng)驗,2+ 年 LLM/Agentic 實戰(zhàn),負責過?產(chǎn)級智能體或 GenAI 應?。 5–8 years in SWE/Data/ML, 2+ years hands-on with LLM/agentic systems in production. 技術棧:精通 Python 或 TypeScript;熟悉 LangGraph/Semantic Kernel/?研編排器 等之?;掌握 FAISS/Milvus/Pinecone/Elasticsearch 任?。 Strong Python or TypeScript; familiar with LangGraph/Semantic Kernel/custom orchestrators; one of FAISS/Milvus/Pinecone/Elasticsearch. ?程能?:具備函數(shù)/?具調?、結構化輸出(JSON/Schema 校驗)、多步規(guī)劃/反思/?修復實踐;能把 業(yè)務規(guī)則固化為 Guardrails。 Proven tool/function calling, structured outputs (JSON/schema validation), multi-step planning/reflection/self-repair; encode rules as guardrails. 溝通:英語流利,能與海外客戶/團隊?效溝通。 Fluent English for effective collaboration with global customers/teams. 加分項(Plus):指令微調/LoRA/DPO、ServiceNow/Salesforce 集成、數(shù)據(jù)駐留實踐。 Nice-to-haves: instruction tuning/LoRA/DPO, ServiceNow/Salesforce integrations, data residency practice.