影石算法集成工程师（S）

1，负责电商数据仓库的ETL流程设计、开发与优化，尤其关注招商、营销活动（含大促）等核心业务场景的数据集成，确保数据的准确性、实时性和为业务决策和AI应用提供高质量数据基础。 2，主导电商领域的数据建模工作，构建满足用户画像、商品分析、营销效果评估等业务需求的多维数据模型，支持精细化运营、个性化推荐和智能决策。 3，与电商业务、招商、营销业务和数据科学等组紧密合作，深入理解业务痛点和增长目标，提供创新的数据解决方案，优化数据处理流程，提升数据赋能业务的能力。 4，参与大数据平台的优化和扩展，探索并应用AI技术（如机器学习、自然语言处理等）提升数据处理效率、数据质量和数据洞察能力，例如智能数据清洗、异常检测、特征工程自动化等。 5，编写高质量的代码和技术文档，确保代码的可维护性、可扩展性和可理解性，并积极参与技术分享和知识沉淀。 1，Responsible for the design, development, and optimization of ETL processes for the e-commerce data warehouse, with a focus on core business scenarios such as merchant acquisition, marketing campaigns (including major promotions), ensuring accurate, real-time, and efficient data transmission, and providing high-quality data foundation for business decisions and AI applications. 2，Lead data modeling efforts in the e-commerce domain, building multi-dimensional data models that meet the business needs of user profiling, product analysis, marketing performance evaluation, etc., supporting refined operations, personalized recommendations, and intelligent decision-making. 3，Collaborate closely with e-commerce business, merchant acquisition, marketing, and other teams to deeply understand business pain points and growth objectives, provide innovative data solutions, optimize data processing workflows, and enhance the ability of data to empower business. 4，Participate in the optimization and expansion of big data platforms, explore and apply AI technologies (such as machine learning, natural language processing, etc.) to improve data processing efficiency, data quality, and data insight capabilities, such as intelligent data cleaning, anomaly detection, and automated feature engineering. 5，Produce high-quality code and technical documentation to ensure code maintainability, scalability, and understandability, and actively participate in technical sharing and knowledge accumulation.

1.智能分析平台研发：主导腾讯云ChatBI 的架构设计，深度融合大模型技术（如 RAG、NL2SQL、NL2DSL），实现自然语言驱动的数据查询与可视化分析能力，推动产品向 AI 原生方向升级。 2.AI 驱动产品设计：负责腾讯云数据分析类产品的智能化迭代，基于 LLM 能力重构交互逻辑（如自然语言语义解析、动态知识注入），打造 “零代码” AI 分析体验，覆盖 SaaS 与私有化部署场景。 3.AI 技术方案落地：根据业务需求输出兼具创新性与可行性的技术方案，主导大模型微调（如领域适配、参数高效优化）、向量数据库集成、智能查询优化等核心模块开发，确保代码质量与工程落地性。 4.智能场景问题攻坚：针对 SaaS 与私有化客户的复杂需求，通过 AI 技术手段（如模型推理优化、实时数据处理）解决智能分析链路中的性能瓶颈、语义歧义等问题，保障 AI 功能在不同部署环境下的稳定性与准确性。

Team Introduction: Dedicated to building an industry-leading large-model dialogue system, the team serves hundreds of millions of daily active users, with application scenarios covering the entire Douyin e-commerce ecosystem. This includes core business scenarios such as platform customer service, platform merchant service, merchant customer service, influencer customer service, and innovative intelligent shopping guides. Through continuous technological innovation and optimization, the team has successfully established a complete intelligent dialogue solution, delivering significant efficiency improvements and user experience enhancements to e-commerce operations. Research Objectives: Develop an LLM-based customer service chatbot for TikTok and Douyin E-commerce, enabling intelligent customer service interactions. The LLM will handle the entire user inquiry process, including request clarification, solution negotiation, and execution. Necessity: LLM's strong conversational and reasoning abilities make it especially suitable for intelligent customer service, capable of potentially reaching the service standards of excellent human representatives. Research Content: Design a multi-agent framework based on LLM, integrating planning-agent, reply-agent, and tool-agent. Each agent will specialize in different functions, working collaboratively to manage the complete service process—from issue identification and solution negotiation to solution implementation and feedback. 1) Reply-agent ensures the proposed solutions comply with platform policies and service guidelines, avoids excessive improvisation or hallucinations, and maintains smooth communication and negotiation with the user. 2) Planning-agent identifies user demands and problem scenarios, sourcing relevant service guidelines and constraints as well as recognizing risk scenarios. 3) Tool-agent validates the legality of tool usage, accurately interprets the results from tool interactions, and manages execution dependencies of various actions. Research Challenges: Compliance with service guidelines: Ensuring the chatbot's solutions adhere to platform service guidelines (such as available refund within xx days of parcel arrival and coupon limits per user per week). Dynamic feedback adaptation: Static adherence to service rules and providing fixed solutions can limit the flexibility of reply-agents, preventing them from acting like excellent human customer service representatives. By enabling reply-agents to interact in real-time with their environment, considering user's behavioral trends, demands expressed during inquiries, and feedback on proposed solutions, personalized service can be provided. This approach fosters adaptive responses and progressive services and solutions, closely mirroring the flexibility and excellence of human customer service. Self-reflection: Employing LLM's capabilities to understand, analyze, and evaluate its own behavior, fostering self-supervision and decision refinement through reflection on outputs, particularly with complex and ambiguous tasks. Complex image processing: Handling scenarios involving numerous complex images (including shipping order photos, bank transaction screenshots, images of damaged goods received, and seller qualification certifications). These images contain key information crucial to enhancing the chatbot's problem resolution capabilities. 团队介绍： 智能对话团队，致力于打造业界领先的大模型对话系统。团队服务的日活用户超过数亿，应用场景覆盖抖音电商全链路，包括平台客服、平台商服、商家客服、达人客服，以及创新的智能导购等核心业务场景，通过持续的技术创新和优化，成功构建了一套完整的智能对话解决方案，为电商业务带来了显著的效率提升和用户体验改善。 课题目标： 构建基于LLM的电商客服机器人（Chatbot），服务TikTok和抖音电商智能客服场景，由LLM完成一次用户进线的完整接待过程，包括诉求澄清、方案协商、方案执行等阶段。 必要性： LLM具有强大的对话和推理能力，智能客服是LLM能够发挥价值的最典型场景，有机会能够达到匹配优秀人工客服的服务能力。 课题内容： 设计一个基于LLM 的 multi-agent framework，将 planning-agent、reply-agent、tool-agent 集成到一起，每个 agent 负责不同能力，互相协同，完成从问题定位、方案协商，到方案执行、结果反馈等服务全流程。reply agent 需要确保给用户提供的方案是符合平台的相关政策和service policy的，不自行过度发挥、不出现幻觉，顺滑的完成和用户的沟通协商过程；planning agent 完成定位用户诉求和问题场景，以便从外部获取该场景的服务准则和约束，如何识别风险场景；tool agent 需要确保工具调用的合法性、接收和解析工具调用的返回结果，另外一些动作的执行存在前后依赖的问题。 课题挑战： 1、遵循服务准则：如何确保方案Chatbot提供的方案是follow平台服务准则的，例如到货xx天之内可以申请退款、同一用户一星期内最多发送xx额度的优惠券； 2、感知环境反馈：reply agent如果只能死板的follow当前场景服务准则，提供一层不变的方案，是无法像优秀客服一样做到灵活变通的。让Agent能够实时的和环境打通，通过结合当前用户进线前的行为动线、进线后表达的诉求和用户对 agent 提供方案的反馈，为用户提供个性化的服务，对用户的实时反馈有响应，像优秀客服一样能随机应变，递进式的提供服务和解决方案； 3、进行自我反思：利用LLM理解、分析和评价其自身的行为，使LLM能够自我监督，通过对自身输出的反思，改进其所做的决策，以便在处理复杂、有歧义的任务时，能有更好的表现； 4、复杂图片理解：电商场景存在大量复杂的图片，包括运费订单实拍图、银行流水截图、买家收货缺件破损的、商家各类资质证明等，这类图片往往包含重要的信息，对提升Chatbot解决能力非常重要。

1. 负责相机、视频会议等产品软件设计与开发工作 2. 负责音视频编解码、渲染、直播等多媒体开发工作 3. 分析解决系统性能问题、系统稳定性问题