Machine-readable resume — fetched and edited by AI agents (Claude, Cursor, ChatGPT) through the cv-pro CLI or MCP. Also served as raw JSON at /biwenshuai.json.
{ "username": "biwenshuai", "header": { "name": "毕文帅", "tagline": "NLP算法工程师 / AI大模型开发工程师 / Agent开发工程师" }, "personalInfo": { "email": "biwenshuai1992@gmail.com", "phone": "", "location": "", "pronouns": "", "mbti": "", "birthday": "" }, "experience": [ { "company": "九坤投资算力业务线", "role": "高级AI应用开发工程师", "startDate": "2025/11", "endDate": "至今", "bullets": [ "负责企业级Agent平台、企业级上下文系统与大规模数据处理系统的设计和开发。", "围绕业务意图、编排、技能和上下文四层架构构建企业级AI应用能力。", "推动多模态混合检索、上下文压缩、权限管理和企业知识库自动化建设落地。" ], "tags": [ "Agent", "LLM应用", "RAG", "MCP", "企业AI平台" ] }, { "company": "华大基因研究院", "role": "自然语言处理高级工程师", "startDate": "2021/08", "endDate": "2024/10", "bullets": [ "负责生信分析Agent系统、时空客服问答系统、文章辅助写作系统和大模型应用基础服务模块等项目。", "结合Agent、RAG、GraphRAG、向量模型微调、rerank模型微调等技术提升科研与生信场景智能化效率。", "参与子痫前期预测、多组学模型融合等科研项目，产出SCI论文和发明专利。" ], "tags": [ "NLP", "Bioinformatics", "Agentic RAG", "知识图谱", "科研AI" ] }, { "company": "诺基亚上海贝尔科技", "role": "NLP算法工程师", "startDate": "2018/08", "endDate": "2021/08", "bullets": [ "负责电信与能源场景中的NLP、机器学习、知识图谱和预测建模项目。", "完成深圳能源烟气预测、北京移动NPS满意度预测、北京移动告警根因分析、浙江移动供应链知识图谱构建等项目。", "通过数据挖掘、图查询封装、质量监控与告警能力，支撑业务分析和流程问题发现。" ], "tags": [ "NLP", "机器学习", "知识图谱", "预测建模", "数据挖掘" ] }, { "company": "中国石油集团", "role": "数据库开发工程师", "startDate": "2015/07", "endDate": "2018/07", "bullets": [ "从事数据库开发相关工作，积累企业级数据系统开发经验。" ], "tags": [ "数据库开发", "数据系统" ] } ], "education": [ { "school": "哈尔滨工业大学", "major": "", "degree": "本科 / 学士学位", "startDate": "2011.09", "endDate": "2015.06" } ], "projectsRecent": [ { "title": "企业级Agent平台开发", "description": "基于Ironclaw打造企业级Agent平台，适配企业场景并提升业务销售效率。", "url": "", "tags": [ "Agent", "LangGraph", "企业AI平台" ] }, { "title": "企业级上下文系统设计以及构建", "description": "将品牌内容、用户反馈、项目文档、创意过程与策略判断转化为可理解、可调用、可演化的企业上下文。", "url": "", "tags": [ "Context Engineering", "RAG", "知识库" ] }, { "title": "生信分析Agent系统开发", "description": "用户输入生信相关数据或任务后，系统自动进行任务拆解、工具调用与任务运行。", "url": "", "tags": [ "Bioinformatics", "Multi-Agent", "MCP" ] } ], "projectsDetailed": [ { "title": "企业级上下文系统设计以及构建", "type": "企业AI平台", "startDate": "2026.1", "endDate": "2026.4", "url": "", "award": "", "bullets": [ "项目描述：将企业大量复杂非结构化信息，包括品牌内容、用户反馈、项目文档、创意过程与策略判断等，转化为可以被理解、被调用、被持续演化的上下文。", "技术实现：企业知识库自动化构建，内容进入系统后自动识别、标注与结构化，从文件存储升级为语义化上下文网络。", "技术实现：通过多模态混合检索打造企业专属决策知识引擎，并实现上下文压缩与渐进式披露。", "技术实现：构建严格权限管理能力，使不同团队、项目和角色拥有差异化上下文管理权限。" ], "tags": [ "Context Engineering", "RAG", "多模态检索", "企业知识库", "权限管理" ] }, { "title": "企业级Agent平台开发", "type": "企业AI平台", "startDate": "2025.11", "endDate": "2026.04", "url": "", "award": "", "bullets": [ "项目描述：基于Ironclaw打造企业级Agent平台，适配大部分企业使用场景，提高企业销量。", "技术实现：构建意图层、编排层、技能层、上下文层四层架构。", "编排层围绕业务意图进行发散式推理，将任务拆解为多条候选执行路径，并基于质量、成本与时延约束进行动态评估。", "技能层覆盖内容生成、OA系统、智能运维和智能研究；上下文层依托企业级上下文系统承载并持续演进企业关键资产。" ], "tags": [ "Agent", "Ironclaw", "任务编排", "企业AI", "智能运维" ] }, { "title": "大规模数据处理系统", "type": "数据工程 / LLM数据处理", "startDate": "2025.11", "endDate": "2026.04", "url": "", "award": "", "bullets": [ "项目描述：将约90T PDF数据转化为模型可训练的数据。", "技术实现：构建大规模数据处理框架，包括状态管理、错误重试、异常识别等模块。", "基于MinerU 2.5识别PDF中的文本、表格、图片和公式。", "基于置信度对识别不准确模块进行标注，并使用大模型重新识别低置信度内容。" ], "tags": [ "数据处理", "PDF解析", "MinerU", "LLM数据", "质量控制" ] }, { "title": "生信分析Agent系统开发", "type": "生信AI / Agent系统", "startDate": "2024.12", "endDate": "2025.03", "url": "", "award": "已部署线上，并得到客户技术团队好评", "bullets": [ "项目描述：用户输入生信相关数据或生信任务后，大模型自动进行任务拆解和任务运行。", "技术实现：构建SupervisorAgent、PlanningAgent、CodeAgent、SearchAgent等多Agent系统框架。", "CoreAgent将生信分析工具自动封装成MCP Server。", "使用GraphRAG技术辅助生信相关代码生成，并基于生信领域语料微调工具调用模型。", "整体框架基于LangGraph实现。" ], "tags": [ "Bioinformatics", "LangGraph", "MCP", "GraphRAG", "工具调用" ] }, { "title": "时空客服问答系统", "type": "智能客服 / RAG", "startDate": "2024.03", "endDate": "2024.10", "url": "", "award": "已部署线上，可以完全替代人工", "bullets": [ "项目描述：具备时空组学相关背景知识，同时能够回答时空云平台相关的各类问题。", "技术实现：结合Agent和RAG技术提升客服系统整体泛化能力。", "负责知识库构建和优化处理、生信领域向量模型微调、rerank模型微调。", "采用混合检索技术和图增强技术提升回答准确率，并支持文本和图表输出。" ], "tags": [ "RAG", "Agent", "混合检索", "rerank", "时空组学" ] }, { "title": "文章辅助写作系统", "type": "科研写作 / Agentic RAG", "startDate": "2024.01", "endDate": "2024.05", "url": "", "award": "已部署上线，显著提升科研人员综述撰写效率和research效率", "bullets": [ "项目描述：帮助用户自动撰写生物相关领域综述文章。", "技术实现：构建文献数据库、文献知识抽取流程和文献知识图谱。", "设计资料收集Agent、OutlineAgent、WriteAgent、润色Agent。", "实现准确知识检索模块，整体框架基于LangChain，Agentic RAG基于LlamaIndex。" ], "tags": [ "LangChain", "LlamaIndex", "Agentic RAG", "知识图谱", "科研写作" ] }, { "title": "子痫前期预测模型（科研）", "type": "科研 / 医疗AI", "startDate": "2023.03", "endDate": "2024.05", "url": "", "award": "发表SCI论文两篇，系统部署于广东省妇幼保健院", "bullets": [ "项目描述：对孕早期女性进行子痫风险预测，辅助提前治疗和保护。", "项目总结：基于多模型融合推理提高预测准确率。" ], "tags": [ "医疗AI", "预测模型", "多模型融合", "SCI" ] }, { "title": "大模型应用基础服务模块", "type": "LLM基础设施", "startDate": "2023.02", "endDate": "2024.03", "url": "", "award": "显著简化大模型应用开发流程，提高开发效率", "bullets": [ "项目描述：统一API服务模块、prompt版本管理器、问答QA测试工具集、自动微调调度器、QA问答数据挖掘和大模型服务调用监控器。", "项目总结：为大模型应用开发提供基础服务能力。" ], "tags": [ "LLMOps", "Prompt管理", "Fine-tuning", "QA评测", "服务监控" ] }, { "title": "多组学模型融合（科研）", "type": "科研 / 多组学", "startDate": "2021.11", "endDate": "2022.05", "url": "", "award": "癌症预测准确率提高5个百分点，发表SCI一篇，发表专利一篇", "bullets": [ "项目描述：将不同组学的底层数据采用融合算法进行融合，提高下游任务准确率。" ], "tags": [ "多组学", "模型融合", "癌症预测", "SCI", "专利" ] }, { "title": "深圳能源烟气预测项目", "type": "工业预测建模", "startDate": "2020.11", "endDate": "2021.05", "url": "", "award": "线上运行结果：10%正负误差准确率达到80.5%，20%正负误差达到99.6%", "bullets": [ "项目描述：基于垃圾焚烧数据预测未来十分钟NOX和HCL值，并对现有数据进行数据质量实时监控和告警。" ], "tags": [ "时间序列预测", "工业数据", "数据质量监控", "告警" ] }, { "title": "北京移动NPS满意度预测", "type": "机器学习 / NLP", "startDate": "未注明", "endDate": "", "url": "", "award": "精准率0.6，召回率0.1，业务更关注精准率", "bullets": [ "项目描述：基于机器学习和NLP技术进行NPS满意度预测。" ], "tags": [ "NLP", "机器学习", "满意度预测" ] }, { "title": "北京移动告警根因分析", "type": "数据挖掘", "startDate": "2021.03", "endDate": "2021.05", "url": "", "award": "已部署线上，帮助专家方便定位根因告警", "bullets": [ "项目描述：基于数据挖掘技术进行告警根因分析。" ], "tags": [ "数据挖掘", "根因分析", "告警分析" ] }, { "title": "浙江移动供应链知识图谱构建", "type": "知识图谱", "startDate": "2020.09", "endDate": "2021.01", "url": "", "award": "", "bullets": [ "项目描述：构建浙江移动供应链知识图谱，用于发现供应链流程问题和供应链可视化。", "项目总结：预先封装基于图的查询语句，便于流程各环节查询、识别和发现问题。" ], "tags": [ "知识图谱", "图查询", "供应链", "可视化" ] }, { "title": "近三年发表的论文与专利", "type": "论文 / 专利", "startDate": "2022", "endDate": "2025", "url": "", "award": "", "bullets": [ "Bi W., Ma, Y., et al. (2024). An entity extraction pipeline for medical text records using large language models. JMIR, 26, e54580. DOI: 10.2196/54580.", "Wang, L., Bi, W., et al. (2024). Investigating the impact of prompt engineering on the performance of large language models for standardizing obstetric diagnosis text: Comparative study. JMIR Formative Research, 8, e53216. DOI: 10.2196/53216.", "Wang, L., Ma, Y., Bi, W., et al. (2024). An early screening model for preeclampsia: Utilizing zero-cost maternal predictors exclusively. Hypertens Res, 47(4), 1051-1062. DOI:10.1038/s41440-023-01573-8.", "Huang R, Yao Y, Tong X, et al., Bi W, et al. (2023). Tracing the evolving dynamics and research hotspots of microbiota and immune microenvironment. Microbiol Spectr, 11(5), e0013523. DOI:10.1128/spectrum.00135-23.", "Bi W, Huang R, Yao Y, Tong X, et al. (2025). Robust multi-omics subtyping of hepatocellular carcinoma. Manuscript in preparation.", "毕文帅, 王雷, 等. (2023). 多源数据融合方法及装置. 中国发明专利（已公开）, 公开号CN119229962A.", "毕文帅, 王雷, 等. (2022). 妊娠期风险预测方法及装置. 中国发明专利（已公开）, 公开号CN118262905A." ], "tags": [ "JMIR", "医疗NLP", "医疗AI", "SCI", "专利" ] } ], "skills": [ { "name": "大模型与LLM开发", "items": [ "精通大型语言模型开发，熟悉Transformer架构、自监督学习、指令微调、模型量化等技术。", "熟练使用Hugging Face、LangChain、LlamaIndex等工具和框架。", "具备Qwen、LLaMA、DeepSeek等开源模型应用与调优经验，熟练掌握prompt优化技巧。" ] }, { "name": "Agent与多Agent系统", "items": [ "精通LLM应用开发和Agent开发技术栈，熟练使用LangGraph、AutoGen、CAMEL等框架。", "掌握Planning、Memory、Tools模块化构建方法，能够设计复杂任务规划、长期记忆管理和工具调用机制。", "熟练掌握MCP相关技能，能够构建高效协作的多Agent系统。" ] }, { "name": "模型定制与推理优化", "items": [ "熟悉Embedding、Fine-tuning、LoRA、QLoRA、量化(INT8/INT4)等大模型定制化技术。", "熟练使用PyTorch、Hugging Face Transformers、PEFT、DeepSpeed、vLLM等训练与推理加速技术。", "具备模型压缩与性能优化经验。" ] }, { "name": "评测、RAG与知识平台", "items": [ "熟悉大模型评估方法与指标，能够构建包含自动化评测和人工评测流程的完整评测体系。", "熟悉Milvus、Pinecone、Chroma等向量数据库和知识库构建技术。", "能够开发高效的检索增强生成(RAG)系统与企业级知识平台，掌握Graph RAG技术提升知识关联性和推理能力。" ] }, { "name": "个人优势与社区贡献", "items": [ "开源社区贡献者，llama3中文版开源贡献者，prompt管理插件开源共享者，langmanus代码贡献者。", "简书签约作者（机器学习、深度学习方向），Botblog.app作者，AgentShare作者。", "对AI相关技术有极大兴趣和热情，学习能力、动手能力、组织能力和抗压能力强。" ] } ], "contact": [ { "label": "Email", "url": "mailto:biwenshuai1992@gmail.com" }, { "label": "简书", "url": "https://www.jianshu.com/u/5634325704f5" }, { "label": "Botblog.app", "url": "https://botblog.app" } ], "meta": { "updatedAt": "2026-06-04T12:24:35.042Z" } }