机器学习工程师，客户体验智能
查看雇主原标题
Machine Learning Engineer, CX IntelligenceCoinbase · Remote - 巴西
职位信息来自雇主公开的招聘页面。申请前请务必在雇主官网核实详情。
为什么值得关注？
发现指数 50/100，仅依据与该职位一起存储的证据计算。
- 新的雇主官方职位
- 远程职位
分数构成
- 时效性 （随职位发布时间变化）+18
- 雇主官方来源+15
- 远程职位+8
- 稀有职位+1
- 公司来源健康度+8
该职位未包含：已披露薪资、提及签证担保、提及搬迁、未出现在监控的职位板上。
这些理由来自雇主自己的职位描述与我们核实过的来源检查结果。除了已存储的信号之外，我们不做任何推测。
职位描述
机器翻译准备好从事你职业生涯中最具影响力的工作了吗？在 Coinbase，我们对增加经济自由的使命毫不妥协。标准很高，环境紧张，而我们喜欢这样。这里不适合安于现状的人，而是一个让你突破自我认知极限的地方。如果你准备好与那些拒绝满足于“足够好”的人一起构建金融的未来，那么这里就是你的归属。Coinbase 是一家远程优先、但并非仅限远程的公司。预计每季度会聚在一起进行名为“surges”的高强度线下工作会议。了解更多关于在 Coinbase 工作的信息。
CX Intelligence Engineering 团队隶属于 Coinbase 的企业应用与架构组织，负责构建为 Coinbase Chat、帮助中心和客服工具提供支持的多智能体平台。作为该团队的机器学习工程师，你将设计和扩展自动化复杂客户支持工作流的智能体系统，将 LLM 与内部 API 和工具连接起来，为数百万客户提供快速、准确且合规的 AI 驱动体验。
岗位职责
• 使用高级编排框架（LangGraph、Google ADK）架构多智能体系统，以端到端自动化复杂的客户支持流程。
• 使用 Model Context Protocol (MCP) 构建和扩展集成，将 LLM 与 Coinbase 内部 API、数据库和第三方工具连接起来。
• 开发自动化的“LLM-as-a-judge”评估流水线，以监控、衡量并改进生产环境中非确定性 AI 智能体的性能。
• 实施 RAG、微调和提示工程技巧，确保聊天机器人回复有据可依、准确，并符合 Coinbase 政策。
• 交付生产就绪的 Python 服务，具备韧性、低延迟，并能够在异步微服务中处理 Coinbase 规模的流量。
• 与 Conversation Design 和产品团队合作，将复杂业务逻辑转化为去中心化架构中可执行的智能体流程。
所需技能和经验：
• 3 年以上构建和扩展生产环境 ML/AI 系统的经验，并具有实施智能体“Loop”或“ReAct”系统的实证经验，其中 AI 可自主采取行动。
• 深入理解 LLM 生命周期，包括上下文窗口管理、token 优化、结构化输出解析（Pydantic、JSON mode）以及多智能体编排框架（LangGraph、Google ADK 或类似框架）。
• 精通 Python，并具有微服务架构、异步编程、高吞吐量 API 和向量数据库（Pinecone、Weaviate 或同等产品）的实操经验。
• 具有向 CX、法务和产品团队等非技术利益相关者解释模型行为和技术权衡的实证能力。
• 负责任地使用生成式 AI，保持人工监督，以交付可用于业务的输出，并推动工作流效率、成本和质量的可衡量改进。
职位 ID：P77545 薪酬透明度通知：该职位的目标年度基本工资范围如下详述。总薪酬还可能包括股权和奖金资格以及福利（包括医疗、牙科和视力）。
年度基本工资范围（不包括股权和奖金）： R$347.900 — R$347.900 BRL
• 申请限制：候选人在 6 个月内最多可提交 3 份申请。
• 平等机会雇主：Coinbase 是平等机会雇主。所有合格申请人都会获得录用考虑，不因种族、肤色、宗教、性别、性取向、性别认同、国籍、残疾、受保护退伍军人身份或遗传信息而受到歧视。有犯罪历史的申请人将根据适用的联邦、州和地方法律予以考虑。
• 美国申请人：查看 Employee Rights、Know Your Rights 和 E-Verify Notice of Participation。
• 便利安排：如果您是需要合理便利的残障人士，请将您的请求和联系信息发送至 accommodations[at]coinbase.com。需要屏幕阅读技术？点击此处下载免费的兼容屏幕阅读器并查看教程。
• 数据隐私与仲裁：提交申请即表示您同意我们的 Candidate Privacy Notice。美国申请人：提交申请即表示您同意 Arbitration of Disputes。
以上内容由机器翻译自动生成，可能存在错误；投递前请以雇主原文为准。
查看雇主原文
职位描述
Ready to do the most impactful work of your career? At Coinbase , we are uncompromising on our mission to increase economic freedom. The bar is high, the environment is intense, and we like it that way. This isn't a place for complacency, it’s a place to be pushed past your perceived limits. If you're ready to build the future of finance alongside people who refuse to settle for "good enough," you belong here. Coinbase is a remote-first, but not remote-only company. Expect to get together quarterly for intense in-person working sessions called “surges.” learn more about working at Coinbase .
The CX Intelligence Engineering team, part of Coinbase's Enterprise Applications and Architecture org, builds the multi-agent platform powering Coinbase Chat, Help Center, and agent tooling. As a Machine Learning Engineer on this team, you'll design and scale the agentic systems that automate complex customer support workflows, connecting LLMs with internal APIs and tools to deliver fast, accurate, and compliant AI-powered experiences for millions of customers.
岗位职责
• Architect multi-agent systems using advanced orchestration frameworks (LangGraph, Google ADK) to automate complex customer support procedures end-to-end.
• Build and scale integrations using Model Context Protocol (MCP) to connect LLMs with internal Coinbase APIs, databases, and third-party tooling.
• Develop automated "LLM-as-a-judge" evaluation pipelines to monitor, measure, and improve the performance of non-deterministic AI agents in production.
• Implement RAG, fine-tuning, and prompt engineering techniques to ensure chatbot responses are grounded, accurate, and compliant with Coinbase policies.
• Ship production-ready Python services that are resilient, low-latency, and capable of handling Coinbase-scale traffic across asynchronous microservices.
• Partner with Conversation Design and Product to translate complex business logic into executable agent procedures within the decentralized architecture.
Required Skills and Experience:
• 3+ years building and scaling ML/AI systems in production, with demonstrated experience implementing agentic "Loop" or "ReAct" based systems where AI takes actions autonomously.
• Deep understanding of the LLM lifecycle including context window management, token optimization, structured output parsing (Pydantic, JSON mode), and multi-agent orchestration frameworks (LangGraph, Google ADK, or similar).
• Strong proficiency in Python with hands-on experience in microservices architecture, asynchronous programming, high-throughput APIs, and vector databases (Pinecone, Weaviate, or equivalent).
• Demonstrated ability to explain model behaviors and technical trade-offs to non-technical stakeholders across CX, Legal, and Product teams.
• Utilizes generative AI responsibly, maintaining human oversight to deliver business-ready outputs and drive measurable improvements in workflow efficiency, cost, and quality.
Job ID: P77545 Pay Transparency Notice: The target annual base salary for this position can range as detailed below. Total compensation may also include equity and bonus eligibility and benefits (including medical, dental, and vision).
Annual base salary range (excluding equity and bonus): R$347.900 — R$347.900 BRL
• Application Limit: Candidates may submit a maximum of 3 applications within a 6-month period.
• Equal Opportunity Employer: Coinbase is an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, protected veteran status, or genetic information. Applicants with criminal histories will be considered consistent with applicable federal, state, and local laws.
• US Applicants: View Employee Rights , Know Your Rights , and E-Verify Notice of Participation.
• Accommodations: If you are an individual with a disability who needs a reasonable accommodation, email us your request and contact info at accommodations[at]coinbase.com. Need screen reading technology? Click here to download a free compatible screen reader and view the tutorial .
• Data Privacy & Arbitration: By submitting your application, you agree to our Candidate Privacy Notice . US applicants: By submitting your application, you agree to Arbitration of Disputes .