资深软件工程师, AI 代理 — 紫色旅程
Staff Software Engineer, AI Agents — Purple Journey
关于Nu
Nu是拉丁美洲领先的数字银行，为巴西、墨西哥和哥伦比亚的1.4亿客户提供服务。公司通过利用数据和专有技术开发创新产品和服务，引领行业变革。
秉承着对抗复杂性并赋能人们的使命，Nu为客户提供完整的金融旅程，通过负责任的贷款和透明度促进金融包容性和进步。公司由一个高效且可扩展的商业模式驱动，结合低成本服务与不断增长的回报。
Nu的影响已获得多项奖项的认可，包括《时代》100家最具影响力公司、《快公司》最具创新力公司以及《福布斯》全球最佳银行。
访问我们的机构页面 https://www.nu.com/2026-en
关于该职位
Purple Journey是Nubank的以AI为核心的表现、人才和学习平台。其代理程序支持评估、校准、持续辅导、等级评定和人员流动等体验——不是单一的聊天机器人，而是一个管理者和Nubank员工可以信赖的系统。
作为AI代理团队的资深软件工程师，您将负责这些代理从头到尾的工作方式：编排、代理设计和工程品质标准。您将确保新代理作为可靠、安全且易于维护的产品发布，而不是一次性演示。
该职位结合了深厚的后端和系统工程与生产AI。您将处理敏感的人事数据、人机协作流程以及分布在巴西、美国和加拿大的高曝光利益相关者。
您将负责
- 设计编排模型：代理如何组合、路由、调度、转交给人类并在多个产品界面和服务中运行。
- 为真实的人事工作流创建和演进代理，包括工具、合同、身份、范围、故障模式和再生策略——不仅仅是提示。
- 通过评估、测试、可观测性、成本和延迟控制、隐私、授权、版本控制、CI门禁和生产事件准备度来建立强大的工程品质标准。
- 构建可靠的基础设施，处理来自多个内部平台的数据，包括协作和知识系统如Slack、Google Docs和Confluence。
- 定义其他工程师和编码代理可以遵循的标准，涵盖架构、评审、技能和合同。
- 与产品、人事、数据、S
查看英文原文
ABOUT NU
Nu is the leading digital bank in Latin America, serving 140 million customers across Brazil, Mexico, and Colombia. The company has been leading an industry transformation by leveraging data and proprietary technology to develop innovative products and services.
Guided by its mission to fight complexity and empower people, Nu caters to customers’ complete financial journey, promoting financial access and advancement with responsible lending and transparency. The company is powered by an efficient and scalable business model that combines low cost to serve with growing returns.
Nu’s impact has been recognized in multiple awards, including Time 100 Most Influential Companies, Fast Company’s Most Innovative Companies, and Forbes World’s Best Banks.
Visit our Institutional Page https://www.nu.com/2026-en
ABOUT THE ROLE
Purple Journey is Nubank’s AI-first platform for performance, talent and learning. Its agents support experiences across assessments, calibration, always-on coaching, leveling and mobility — not as a single chatbot, but as a system that managers and Nubankers can trust.
As a Staff Software Engineer, AI Agents, you will own how these agents work end to end: orchestration, agent design and the engineering quality bar. You will help ensure that new agents ship as reliable, secure and maintainable products—not one-off demonstrations.
This role combines deep backend and systems engineering with production AI. You will work with sensitive People data, human-in-the-loop workflows and high-exposure stakeholders across Brazil, the United States and Canada.
YOU’LL BE RESPONSIBLE FOR
- Designing the orchestration model: how agents are composed, routed, scheduled, handed off to humans and operated across product surfaces and services.
- Creating and evolving agents for real People workflows, including tools, contracts, identity, scope, failure modes and regeneration strategies—not only prompts.
- Establishing a strong engineering quality bar through evaluations, testing, observability, cost and latency controls, privacy, authorization, versioning, CI gates and production incident readiness.
- Building reliable infrastructure to process data from multiple internal platforms, including collaboration and knowledge systems such as Slack, Google Docs and Confluence.
- Defining standards that other engineers and coding agents can follow across architecture, reviews, skills and contracts.
- Partnering with Product, People, Data, Security, Compliance and platform teams to align technical decisions with business and user needs.
- Mentoring engineers and helping raise the technical bar across a growing, cross-functional team.
- Supporting the safe adoption of AI-powered products by engineers and non-engineers across Nubank.
WE ARE LOOKING FOR A PERSON WHO HAS
Required
- Proven Staff-level technical leadership delivering complex software systems in production.
- Hands-on experience with production agent or LLM systems, including orchestration, tool use, structured outputs and real-world failure modes.
- Strong backend and systems engineering experience across multiple services, contracts, authentication, authorization and data flows.
- A high bar for quality and operability, including evaluations, testing, monitoring, incident response and continuous improvement.
- Experience designing systems that handle sensitive data, privacy constraints and human-in-the-loop product decisions.
- Ability to work through ambiguity, make architectural trade-offs and influence senior stakeholders.
- Strong written and verbal communication skills in English.
- Willingness to work in a hybrid model from an approved Nubank office location.
Nice to have
- Experience with People, HR, talent, performance or learning products.
- Experience building AI systems in regulated or privacy-sensitive environments.
- Familiarity with agent evaluation frameworks, prompt and context management, tool contracts or multi-agent architectures.
- Experience working across international teams and multiple time zones.
LOCATION FOR THIS OPPORTUNITY
This role can be based in an approved Nubank hub in:
- Brazil
- United States
- Canada
Specific office location will be confirmed during the process.
WORK MODEL FOR THIS ROLE
- Hybrid 2–3 times/week: Our hybrid work model brings us to the office at least twice a week, on strategic days designed to maximize connection and collaboration. For more details, visit https://building.nubank.com/nu-hybrid-work-model/
OUR BENEFITS
Benefits vary by country and local regulations, but generally include:
- Health Insurance
- Life Insurance
- Extended maternity and paternity leaves
- Nucleo – our learning platform of courses
- NuLanguage – our language learning program
- NuCare – our mental health and wellness assistance program
- Vacations
- Work-from-home Allowance
- Opportunity of earning equity at Nu
Additional benefits and eligibility details will be shared during the process.
Our recruitment process may involve the use of artificial intelligence–enabled tools, such as automated interview transcription and analysis, to support the evaluation process. Artificial intelligence is not used to make final hiring decisions; all decisions are made by human reviewers.