
零一万物AI全栈开发工程师
社招全职研发地点:北京状态:招聘
任职要求
技术栈:Python / React / LangGraph / Milvus / PGVector / Elasticsearch / etc. 经验要求:5年+ 1. Python 后端扎实:FastAPI(或等价)、异步/并发、任务队列、系统设计与性能优化。 2. React 前端扎实:能交付ToB用户界面和管理界面的复杂交互(流程编排 / 可视化 / 调试面板),熟悉工程化与状态管理。 3. 熟悉 LangGraph 或同类状态机 / 编排思想,能实现:状态持久化、重试与补偿、分支与回滚、人工介入(HITL)。 4. 熟悉 Milvus / PGVector / ES 的检索体系与 RAG 工程,理解混合检索、重排与引用溯源的工程化落地。 5. 熟悉ToB关键能力:多租户隔离、RBAC…
登录查看完整任职要求
微信扫码,1秒登录
工作职责
1. 构建与迭代B端Agent平台与产品能力:工作流编排(DAG / State Machine)、多智能体协作、会话与任务系统(异步/长任务)、记忆与上下文管理。 2. 负责 Agent 工具体系工程化:工具注册/版本与兼容策略、参数 Schema(JSON Schema/Pydantic)、鉴权与租户隔离、幂等/重试/限流、失败降级、回放与审计。 3. 落地企业级 RAG:多源数据接入(文档 / DB / ES / 内网系统)、切分与索引、混合检索(Milvus / PGVector + ES)、重排、引用溯源、增量更新、权限过滤(ACL / RBAC / ABAC)。 4. 负责全栈交付:React 界面(用户界面和管理界面)、Python 后端(API、队列、调度、权限、审计、配置)。 5. 负责模型接入与路由:公有云与自建推理的统一适配层(Provider / Adapter)、模型路由策略、降级与容灾、成本与延迟优化(缓存、批处理、并发控制、token 预算)。 6. 负责交付与运维工程化:SaaS 多租户与配额;私有化安装包(K8s / Helm + Docker Compose)、离线依赖(镜像 / 包 / 模型 / 向量库)打包、升级迁移与回滚预案。 7. 建立评测与可观测:离线评测集、线上指标(成功率 / 工具成功率 / 引用命中率 / 延迟 / 成本)、A/B与回归门禁;基于Tracing / Metrics / Logs 实现端到端定位与复现。
包括英文材料
Python+
https://liaoxuefeng.com/books/python/introduction/index.html
中文,免费,零起点,完整示例,基于最新的Python 3版本。
https://www.learnpython.org/
a free interactive Python tutorial for people who want to learn Python, fast.
https://www.youtube.com/watch?v=K5KVEU3aaeQ
Master Python from scratch 🚀 No fluff—just clear, practical coding skills to kickstart your journey!
https://www.youtube.com/watch?v=rfscVS0vtbw
This course will give you a full introduction into all of the core concepts in python.
React+
[英文] Quick Start - React
https://react.dev/learn
This page will give you an introduction to 80% of the React concepts that you will use on a daily basis.
https://www.youtube.com/watch?v=SqcY0GlETPk
Master React 18 with TypeScript! ⚛️ Build amazing front-end apps with this beginner-friendly tutorial.
https://www.youtube.com/watch?v=x4rFhThSX04
Learn modern React basics in the most interactive, hands-on way possible in the full course for beginners.
Milvus+
[英文] Tutorials Overview
https://milvus.io/docs/tutorials-overview.md
This page provides a list of tutorials for you to interact with Milvus.
https://www.baeldung.com/milvus-tutorial-intro
In this tutorial, we’ll explore Milvus, a highly scalable open-source vector database.
https://www.youtube.com/watch?v=7ejr_ZzU9jw
Discover the power of Milvus, an open-source vector database revolutionizing AI applications.
https://www.youtube.com/watch?v=Yhv19le0sBw
Vector databases have been trending recently as they power modern search, recommendations, and AI-driven applications.
ElasticSearch+
https://www.youtube.com/watch?v=a4HBKEda_F8
Learn about Elasticsearch with this comprehensive course designed for beginners, featuring both theoretical concepts and hands-on applications using Python (though applicable to any programming language). The course is structured in two parts: first covering essential Elasticsearch fundamentals including index management, document storage, text analysis, pipeline creation, search functionality, and advanced features like semantic search and embeddings; followed by a practical section where you'll build a real-world website using Elasticsearch as a search engine, working with the Astronomy Picture of the Day (APOD) dataset to implement features such as data cleaning pipelines, tokenization, pagination, and aggregations.
FastAPI+
https://fastapi.tiangolo.com/tutorial/
This tutorial shows you how to use FastAPI with most of its features, step by step.
https://realpython.com/get-started-with-fastapi/
FastAPI is a web framework for building APIs with Python.
https://www.youtube.com/watch?v=rvFsGRvj9jo
This video today is a crash course, where we will go through the basics of FastAPI.
系统设计+
https://roadmap.sh/system-design
Everything you need to know about designing large scale systems.
https://www.youtube.com/watch?v=F2FmTdLtb_4
This complete system design tutorial covers scalability, reliability, data handling, and high-level architecture with clear explanations, real-world examples, and practical strategies.
还有更多 •••
相关职位
社招A243655
1、负责抖音AI产品的整体和细节方案的设计和实现,包括但不限于AI活动生成、站点生成、代码生成等方向; 2、负责AI产品涉及的Agent开发、数据工程、业务策略等开发工作; 3、挖掘AI产品在业务上的落地场景,深度探索AI业务提效方式,负责将复杂的AI功能交互以直观、易用的方式呈现给用户,并不断提升效率和用户体验; 4、持续跟进LLM领域的最新技术趋势,结合AI产品需求,提供创新的交互解决方案,并推动技术的迭代和升级。
更新于 2025-03-11北京
社招A27920A
1、负责抖音开放平台,包含小程序、抖音开放平台SDK等千万级DAU产品研发,与产品团队合作推动业务落地,保障用户体验与产品性能,积极探索AI大模型结合小程序在多场景落地,包括但不限于:端侧AI大模型、AI智能小程序、AI内容理解等; 2、负责AI应用平台研发工作,包含AI智能体等产品研发,与产品团队合作推动AI创新产品以及AI业务落地; 3、调研和跟踪AI行业的前沿技术趋势,持续吸收并推进最新AI行业技术在实际应用场景中落地。
更新于 2026-03-02深圳
社招5年以上
1. 负责AI Agent产品的完整设计和开发,包括产品架构设计、功能实现和用户体验优化; 2. 具备完整的AI Agent开发经验,熟悉提示词工程、上下文管理; 3. 具备全栈开发能力,能够独立完成前端、后端、数据库的完整项目开发; 4. 精通Python MCP/Function Call开发,能够构建高效的AI工具调用系统; 5. 具备RAG知识库系统设计和优化能力,了解RAG技术发展历程和适用场景;
更新于 2026-04-08广州
