Job Description

多模态对话系统实习生（机器人交互方向）上海实习职位描述1. 参与多模态对话系统原型搭建
协助搭建机器人对话链路，包括用户输入、上下文管理、模型调用、结构化输出、工具调用和最终回复生成。
2. 参与多轮对话状态管理
设计和维护 session state、task state、user feedback、current target、scene phase 等基础状态，支持多轮对话、任务续接和失败恢复。
3. 参与结构化输出设计与校验
支持模型稳定输出结构化字段，例如 speech_act、intent、emotion_style、tool_call、route、confidence、need_clarification 等，并进行 JSON / Schema 校验。
4. 参与 Agent / Tool Use 原型开发
接入简单工具或技能调用，例如查询、导航、介绍、确认、澄清、任务切换等，支持 Demo 场景下的可执行交互。
5. 参与端侧 / 云端路由实验
协助构造 local / cloud 对比样本，支持 LOCAL_FINAL、LOCAL_PROVISIONAL、CLOUD_FINAL、SAFE_FALLBACK 等策略验证。
6. 参与主动交互与澄清逻辑实现
支持主动问候、主动澄清、任务恢复、失败重试等对话能力原型，例如“请问刚才是哪位在问我？”、“我继续刚才的话题”。
7. 参与 Demo 场景对话脚本工程化
将 Demo 场景中的对话流程、交互策略和模型输出格式落成可运行的原型链路。
8. 参与 case 分析与问题定位
分析对话失败原因，包括模型理解错误、状态丢失、工具调用失败、结构化输出错误、路由错误等。职位要求1. 本科及以上在读，计算机、人工智能、软件工程、自动化、机器人、电子信息等相关专业优先。
2. 熟悉 Python，具备基本工程开发能力，能够编写清晰、可维护的脚本和服务逻辑。
3. 了解 LLM / VLM / RAG / Agent / Tool Use / Function Calling 等基本概念。
4. 有多轮对话、RAG、Agent、问答系统、机器人交互、智能座舱、语音助手等项目经验者优先。
5. 理解 JSON / Schema / Pydantic / API 调用等结构化输出与接口约束方式。
6. 对机器人交互、多模态对话、端云协同、主动交互和服务场景智能体有兴趣。
7. 具备较好的问题拆解能力，能将“对话体验问题”拆成状态、模型、工具、路由或数据问题。
加分项
1. 做过 RAG 系统，包括 BM25、向量检索、FAISS、reranker、query rewrite 等。
2. 做过 Agent / Tool Use / Planning / Router / 多轮状态管理项目。
3. 做过 Qwen、InternVL、MiniCPM、LLaVA、GPT-4o、Claude 等模型的应用或微调。
4. 做过结构化输出、JSON 校验、function calling、tool calling、Pydantic / JSON Schema 约束。
5. 做过智能座舱、语音助手、机器人、数字人、客服助手等对话系统。
6. 有 Redis、FastAPI、vLLM、LangChain、LlamaIndex、Gradio、Streamlit 等工具经验。
7. 有多模态模型项目经验，尤其是图像/视频 + 文本的理解与交互任务。投递

About AGIBOT

AgiBot builds world-leading general-purpose embodied robots and their application ecosystem by pioneering into the fusion and innovation of AI and robotics. AgiBot was founded in February 2023 by seasoned industry experts, including core executives from global technology leaders and top AI scientists. During its development, AgiBot has received ardent support and guidance from senior Chinese leaders. It has been invited on multiple occasions to serve as an industry representative and brief on the progress of the embodied intelligence sector.

Leveraging its industry-leading “1 Ontology + 3 Intelligence Interaction” architecture - built on the robotic embodiment that integrates manipulation, interaction, and locomotion intelligence - AgiBot has launched three robot series (AgiBot A2, Genie, and AgiBot X2) and the industry's first universal embodied foundation model, the "Genie Operator-1 (GO-1)”. This makes AgiBot the only company in the sector with a full product portfolio and comprehensive scenario coverage. AgiBot has also established a leading full-stack ecosystem to empower partners and enable transformation across a wide range of industries.

With its cutting-edge product technologies and eco-system, AgiBot is one of the world's first companies to accomplish large-scale production and commercial deployment of embodied robots, with its products now available in multiple countries and regions. In January 2025, AgiBot made history by mass-producing its 1,000th general-purpose embodied robot, setting a new industry milestone.

Industry

Manufacturing & Production

Company Size

51-200 employees

Headquarters

Shanghai, CN

Year Founded

Unknown

Website

zhiyuan-robot.com

Social Media