🌏 全球远程工作机会汇总

在招 0 仅中国地区远程 0 👁 累计浏览 1136 更新时间

后端工程师(Python),AI 工程:智能体基础

Backend Engineer (Python),AI Engineering: Agent Foundations

全球可投 开发

🏢 公司 / 雇主

GitLab

发布于 — · 首次收录 2026-11-16 · 最后确认在线 2026-11-16 · 👁 浏览 2 次

🛠 技能要求

PythonLangChainLangGraphRESTGraphQLgRPCpytestRuby on RailsJavaScriptVue

📋 职位要求

  • 为 Duo Agent Platform 开发、发布并维护功能,涉及 Duo Workflow Service、AI Gateway,以及在需要时的 GitLab 单体应用,并保持其安全、经过充分测试且高性能。 Develop, ship and maintain features for the Duo Agent Platform in the Duo Workflow Service, the AI Gateway and, where needed, the GitLab monolith. Keep them secure, well-tested and performant.
  • 使用 LangChain 和 LangGraph 构建和改进智能体流程及其可复用组件,包括 Flow Registry。 Build and improve agentic flows and their reusable parts with LangChain and LangGraph, including the Flow Registry.
  • 设计、实现并评审 API(包括 GraphQL 和 REST)及其背后的后端逻辑,为 GitLab 单体应用、IDE 扩展和 Duo CLI 等客户端提供可靠、可扩展且清晰的契约。 Design, implement and review APIs (including GraphQL and REST) and the backend logic behind them, with reliable, scalable and clear contracts for clients such as the GitLab monolith, IDE extensions and Duo CLI.
  • 改进和扩展自动化测试(pytest 和其他框架),包括对智能体和流程行为的评估,以强化质量并为开发者提供更快的反馈。 Improve and extend automated testing (pytest and other frameworks), including evaluations of agent and flow behavior, to strengthen quality and give developers faster feedback.
  • 参加 Tier 2 值班轮换,排查生产问题,参与根因分析,并改进可观测性与弹性。 Join Tier 2 on-call rotations to troubleshoot production issues, contribute to root cause analysis, and improve observability and resiliency.
  • 具备构建和维护生产级 Python 后端应用的经验,包括 API、异步或后台处理以及数据模型。 Experience building and maintaining production Python backend applications, including APIs, asynchronous or background processing, and data models.
  • 具有使用 LangGraph 等 LLM 应用框架的经验,或设计和交付 AI 驱动的后端功能或框架的经验。 Experience with LLM application frameworks such as LangGraph, or designing and shipping AI-powered backend features or harnesses.
  • 擅长设计或扩展 API(REST、GraphQL 或 gRPC),注重可扩展性、可维护性和向后兼容性。 Skill in designing or extending APIs (REST, GraphQL or gRPC) with attention to scalability, maintainability and backward compatibility.
  • 能够在成熟代码库中自如地进行跨全栈工作。 Comfort working across the stack in a mature codebase.
  • 熟悉 Ruby on Rails 和/或 JavaScript 与 Vue 者加分。 Familiarity with Ruby on Rails and/or JavaScript and Vue is a plus.
  • 具备发现和修复应用性能瓶颈的经验。 Experience finding and fixing performance bottlenecks in applications.
  • 具备清晰的书面和口头沟通能力,包括技术提案和文档撰写,能在远程、异步、跨职能团队中工作。 Clear written and verbal communication, including technical proposals and documentation, in a remote, async, cross-functional team.

📄 职位描述(中文)

GitLab 是 DevSecOps 的智能编排平台。GitLab 帮助组织提升开发人员生产力、提高运营效率、降低安全与合规风险,并加速数字化转型。超过 5000 万注册用户和超过 50% 的《财富》100 强企业*信任 GitLab,以更快地交付更好、更安全的软件。我们产品中内建的同样原则也体现在团队的工作方式中:我们将 AI 作为核心生产力倍增器,所有团队成员都应在日常工作流程中融入 AI,以提升效率、创新和影响力。GitLab 是让职业加速、创新蓬勃发展的地方,每个声音都受到重视。我们以价值观和持续的知识交流驱动的高绩效文化,使团队成员能够在与行业领导者协作解决复杂问题的同时充分发挥潜力。与我们一起共创未来,构建改变世界软件开发方式的技术。* Fortune 500® 是 Fortune Media IP Limited 的注册商标,经授权使用。该声明基于 GitLab 数据。《财富》100 强指 2025 年 6 月发布的 2025 年《财富》500 强榜单中排名前 20% 的公司。Fortune 及 Fortune Media IP Limited 与 GitLab 无关联,也不认可 GitLab 的产品或服务。 职位概览 作为 GitLab Agent Foundations 阶段的中级后端工程师(Python),你将超越仅仅使用 AI 工具的层面:你将帮助构建 GitLab 智能体 AI 体验的基础——这个平台让 AI 智能体能够在整个软件交付生命周期中工作,而不仅仅是编写代码。这包括构成智能体与流程的可复用构建块,以及我们的核心框架 Duo Developer。你的大部分工作将是用 Python 进行后端开发,使用 LangGraph 等库在我们的 AI Gateway 中构建安全、可靠且可扩展的功能。在需要时,你也需要跨全栈工作。你将与该阶段及其他 AI 工程团队的工程师紧密合作。这是 GitLab 核心平台与其 AI 战略交汇的高可见度领域。 工作职责 为 Duo Agent Platform 开发、发布并维护功能,涉及 Duo Workflow Service、AI Gateway,以及在需要时的 GitLab 单体应用,并保持其安全、经过充分测试且高性能。使用 LangChain 和 LangGraph 构建和改进智能体流程及其可复用组件,包括 Flow Registry。与产品管理、UX、前端、后端和 AI 专家合作,细化需求,并以小迭代方式交付改进。设计、实现并评审 API(包括 GraphQL 和 REST)及其背后的后端逻辑,为 GitLab 单体应用、IDE 扩展和 Duo CLI 等客户端提供可靠、可扩展且清晰的契约。改进和扩展自动化测试(pytest 和其他框架),包括对智能体和流程行为的评估,以强化质量并为开发者提供更快的反馈。与其他工程师分享标准、模式和心得,提升负责任 AI 集成与证据驱动工程的标准。参加 Tier 2 值班轮换,排查生产问题,参与根因分析,并改进可观测性与弹性。关注竞争格局,随着越来越多的工作走向智能体化,帮助 GitLab 的智能体平台保持一流水准。 任职要求 具备构建和维护生产级 Python 后端应用的经验,包括 API、异步或后台处理以及数据模型。具有使用 LangGraph 等 LLM 应用框架的经验,或设计和交付 AI 驱动的后端功能或框架的经验。擅长设计或扩展 API(REST、GraphQL 或 gRPC),注重可扩展性、可维护性和向后兼容性。能够在成熟代码库中自如地进行跨全栈工作。熟悉 Ruby on Rails 和/或 JavaScript 与 Vue 者加分。具备发现和修复应用性能瓶颈的经验。具备清晰的书面和口头沟通能力,包括技术提案和文档撰写,能在远程、异步、跨职能团队中工作。乐于学习并应用相关技术或领域的技能。 团队介绍 Agent Foundations 阶段构建 GitLab 智能体 AI 体验的基础。我们提供帮助团队向客户交付弹性智能体和流程的平台、目录和执行功能。该阶段下设三个小组:Agent Developer、AI Catalog 和 Agent Execution。它们分别负责 GitLab Duo Developer 基础流程和 Flow Registry;AI Catalog(包括自定义智能体、自定义流程和外部智能体集成);以及智能体执行、智能体工具和智能体可观测性。我们的工程师在 EMEA、AMER 和印度时区以异步优先的方式工作。我们与 AI 工程及 GitLab 其他各个团队合作,使 Duo Agent Platform 能够支撑 GitLab 的众多 AI 功能。 GitLab 对全职员工的支持 支持健康、财务和身心健康的福利;弹性带薪休假;团队成员资源小组;股权激励与员工股票购买计划;成长与发展基金;育儿假。 请注意,我们欢迎不同经验水平的候选人对该职位表达兴趣;许多成功的候选人并未满足每一项要求。此外,研究表明,来自代表性不足群体的求职者往往只有在满足全部条件时才会申请职位。如果你对这个职位感兴趣,请提交申请,让我们的招聘人员来评估你的申请。 国家招聘指南:GitLab 在全球各国招聘新团队成员。我们所有职位均为远程办公,但某些职位可能附带基于所在地的特定资格要求。在启动招聘流程后,我们的招聘团队可以解答有关地点的任何问题。隐私政策:请查阅我们的招聘隐私政策。
🇬🇧 查看英文原文(Original description)
GitLab is the intelligent orchestration platform for DevSecOps. GitLab enables organizations to increase developer productivity, improve operational efficiency, reduce security and compliance risk, and accelerate digital transformation. More than 50 million registered users and more than 50% of the Fortune 100* trust GitLab to ship better, more secure software faster. The same principles built into our products are reflected in how our team works: we embrace AI as a core productivity multiplier, with all team members expected to incorporate AI into their daily workflows to drive efficiency, innovation, and impact. GitLab is where careers accelerate, innovation flourishes, and every voice is valued. Our high-performance culture is driven by our values and continuous knowledge exchange, enabling our team members to reach their full potential while collaborating with industry leaders to solve complex problems. Co-create the future with us as we build technology that transforms how the world develops software. * Fortune 500® is a registered trademark of Fortune Media IP Limited, used under license. Claim based on GitLab data. Fortune 100 refers to the top 20% ranked companies in the 2025 Fortune 500 list, published in June 2025. Fortune and Fortune Media IP Limited are not affiliated with, and do not endorse products or services of GitLab. An overview of this role As an Intermediate Backend Engineer (Python) in GitLab's Agent Foundations stage, you'll go beyond using AI tools. You'll help build the foundations for GitLab's agentic AI experiences: the platform that lets AI agents work across the whole software delivery lifecycle, not just write code. That covers the reusable building blocks agents and flows are made from as well as our core harness, Duo Developer. Most of your work will be backend engineering in Python, using libraries such as LangGraph to build secure, reliable and scalable features in our AI Gateway. You'll also work across the stack where needed. You'll work closely with engineers across the stage and other AI Engineering teams. This is a high-visibility area where GitLab's core platform meets its AI strategy. What you'll do Develop, ship and maintain features for the Duo Agent Platform in the Duo Workflow Service, the AI Gateway and, where needed, the GitLab monolith. Keep them secure, well-tested and performant. Build and improve agentic flows and their reusable parts with LangChain and LangGraph, including the Flow Registry. Work with Product Management, UX, frontend, backend and AI specialists to refine requirements and ship improvements in small iterations. Design, implement and review APIs (including GraphQL and REST) and the backend logic behind them, with reliable, scalable and clear contracts for clients such as the GitLab monolith, IDE extensions and Duo CLI. Improve and extend automated testing (pytest and other frameworks), including evaluations of agent and flow behavior, to strengthen quality and give developers faster feedback. Share standards, patterns and learnings with other engineers to raise the bar for responsible AI integration and evidence-driven engineering. Join Tier 2 on-call rotations to troubleshoot production issues, contribute to root cause analysis, and improve observability and resiliency. Keep an eye on the competitive landscape to help keep GitLab's agent platform best-in-class as more work becomes agentic. What you'll bring Experience building and maintaining production Python backend applications, including APIs, asynchronous or background processing, and data models. Experience with LLM application frameworks such as LangGraph, or designing and shipping AI-powered backend features or harnesses. Skill in designing or extending APIs (REST, GraphQL or gRPC) with attention to scalability, maintainability and backward compatibility. Comfort working across the stack in a mature codebase. Familiarity with Ruby on Rails and/or JavaScript and Vue is a plus. Experience finding and fixing performance bottlenecks in applications. Clear written and verbal communication, including technical proposals and documentation, in a remote, async, cross-functional team. Openness to learning and to applying skills from related technologies or fields. About the team The Agent Foundations stage builds the foundations for GitLab's agentic AI experiences. We provide the platform, catalog and execution features that help teams deliver resilient agents and flows to customers. The stage has three groups: Agent Developer, AI Catalog and Agent Execution. Between them, they own the GitLab Duo Developer foundational flow and the Flow Registry; the AI Catalog, including custom agents, custom flows and external agent integrations; and agent execution, agent tools and agent observability. Our engineers work async-first across EMEA, AMER, and India timezones. We work with teams across AI engineering and the rest of GitLab so the Duo Agent Platform can power many of GitLab's AI features. How GitLab Supports Full-Time Employees Benefits to support your health, finances, and well-being Flexible Paid Time Off Team Member Resource Groups Equity Compensation & Employee Stock Purchase Plan Growth and Development Fund Parental Leave Please note that we welcome interest from candidates with varying levels of experience; many successful candidates do not meet every single requirement. Additionally, studies have shown that people from underrepresented groups are less likely to apply to a job unless they meet every single qualification. If you're excited about this role, please apply and allow our recruiters to assess your application. Country Hiring Guidelines: GitLab hires new team members in countries around the world. All of our roles are remote, however some roles may carry specific location-based eligibility requirements. Our Talent Acquisition team can help answer any questions about location after starting the recruiting process. Privacy Policy: Please review our Recruitment Privacy Policy. Your privacy is important to us. GitLab is proud to be an equal opportunity workplace and is an affirmative action employer. GitLab’s policies and practices relating to recruitment, employment, career development and advancement, promotion, and retirement are based solely on merit, regardless of race, color, religion, ancestry, sex (including pregnancy, lactation, sexual orientation, gender identity, or gender expression), national origin, age, citizenship, marital status, mental or physical disability, genetic information (including family medical history), discharge status from the military, protected veteran status (which includes disabled veterans, recently separated veterans, active duty wartime or campaign badge veterans, and Armed Forces service medal veterans), or any other basis protected by law. GitLab will not tolerate discrimination or harassment based on any of these characteristics. See also GitLab’s EEO Policy and EEO is the Law . If you have a disability or special need that requires accommodation , please let us know during the recruiting process .