Role Description Rockstar is recruiting for an innovative AI company building the back office for accounting firms. They combine the judgment of experienced operators with the leverage of AI agents and reliable software to automate the most complex manual workflows inside CPA firms: tax preparation, bookkeeping, document collection, cleanup, review, close, and client operations. Their platform is already deployed with accounting firms across the country, helping them serve more clients, reduce bottlenecks, and give their best people time back for higher-value work. You will work across product, design, engineering, and implementation. Some days that means: - Mapping how tax packages move through a firm. - Building a review workflow. - Designing an agent loop. - Tightening data models. - Debugging why a customer workflow failed in production. This is a product engineering role for someone who wants to build the system, not just spec it. You will turn what we learn from firms into durable product: - Interfaces - Automations - Review loops - Workflow primitives - Data models - Agent behavior that works across customers The client is vertically integrated across software, AI agents, and managed back-office operations. That makes the problems unusually concrete: - If the product is wrong, the work breaks. - If the product is right, firms can take on more clients without adding headcount. What You Will Do - Own core product workflows for tax prep, tax review, bookkeeping, client requests, and practice-management operations. - Design and build product abstractions that turn messy accounting work into repeatable, reviewable systems. - Use the client's internal agent platform to move from product context to working software quickly, then inspect the result until it is right. - Build interfaces, workflow states, data models, and agent behavior that hold up in live customer usage. - Codify repeatable patterns from customer deployments back into the main product. - Use the product yourself, inspect logs and data when needed, notice what is wrong, and push until the details are right. What You Will Do in Your First 30 Days - Learn how CPA firms move work from source documents to reviewed tax packages, books, and client follow-ups. - Shadow existing client workflows and identify places where better product behavior would remove real manual work. - Pick workflows and turn them into a concrete product plan: inputs, user-facing states, edge cases, success criteria, and verification steps. - Drive an AI-agent implementation loop from product plan to working feature. - Test the workflow yourself against real or realistic data, fix the rough edges, and help ship it into a live customer or internal operator workflow. Who We Are Looking For - You have strong programming skills and have shipped production applications, serious internal tools, or customer-facing automation. - You have high agency and can navigate ambiguity in messy customer environments where the problem is not handed to you cleanly. - You have an ownership mentality and are willing to do whatever it takes to make something work. - You have good communication skills to explain technical tradeoffs and earn trust with non-technical stakeholders. - You are comfortable using AI coding agents as your main implementation tool and holding their output to a high bar. Skills - AI Agents - React - Swift - TypeScript - Docker - PostgreSQL Bonus Points - Experience in accounting, finance, tax, audit, professional services, or another workflow-heavy enterprise vertical. - Previous founder experience or meaningful ownership at an early-stage startup. Compensation - Base Salary: $150,000–$225,000 - Equity: 0.25%–1.00% equity About the Interview - Intro conversation about your background and what you have built. - Practical product/workflow exercise using a real or realistic back-office workflow. - Founder conversation focused on taste, pace, customer empathy, and how you work with AI agents.

• Participate in knowledge transfer activities with the incumbent team for seamless onboarding. • Analyze business requirements, design technical solutions, and develop enterprise applications using Mendix. • Collaborate with Java Engineers to develop custom components and integrations. • Troubleshoot and resolve application defects and performance issues. • Work closely with Business Analysts and stakeholders during Agile ceremonies. • Mentor team members and promote development best practices.

Role Description 我们正在寻找一位全栈工程师，参与核心 AI Agent 产品从架构设计、能力建设到生产落地的完整过程。你将参与 Web 产品、API 服务、Agent 编排系统、后台任务系统、数据层和部署流程等多个环节，和团队一起构建面向真实生产环境的 AI Agent 产品。 你将深度参与 AI Agent 系统的工程化建设，包括： - Agent Loop - 工具调用 - 任务编排 - 多步骤执行 - 上下文管理 - 模型路由 - 异步任务处理 - 结果持久化 - 错误恢复 - 日志追踪与系统可观测性 这个岗位适合对 AI Agent、LLM 应用工程、复杂 Web 产品和系统工程都有强烈兴趣的全栈工程师。 你的主要职责包括： - 参与 AI Agent 产品的全生命周期开发，包括 Web 体验、API 服务、Agent 编排、工具调用、Agent Loop、任务规划、执行反馈、状态管理和结果持久化。 - 设计和实现面向生产环境的 Agent 产品能力，包括 API 服务、任务队列、异步流程、数据模型、权限、计费和业务状态管理等核心模块。 - 构建和优化 Agent 与工具系统之间的调用链路，提升执行稳定性、可观测性、容错能力和扩展能力。 - 参与多 Agent 协作、工具路由、上下文管理、模型选择、任务重试、异常恢复等复杂工程问题的设计与落地。 - 参与 Web 应用开发与维护，完成产品功能、交互流程、前端状态管理和用户体验优化。 - 负责 API 服务、后台任务系统、数据层、Monorepo 工程化及 Docker 部署流程的开发、优化与维护。 - 与产品、设计和工程团队协作，将 AI 能力转化为稳定、可交付、可规模化的产品功能。 - 持续探索 AI 辅助开发和 Agent 工程最佳实践，输出高质量、可维护、可测试的代码。 Qualifications - 精通 TypeScript，熟悉 React、Next.js，具备完整 Web 应用开发经验。 - 精通 Node.js，具备扎实的服务端开发能力和 API 设计能力。 - 熟悉 Hono、Express 或同类 Node.js 服务框架，能够构建高性能、可维护的后端服务。 - 熟悉 AI Agent 相关工程体系，包括 Agent Loop、Tool Calling、任务编排、上下文管理、工具执行、状态追踪和结果持久化。 - 熟练使用 PostgreSQL、Prisma 进行数据建模、查询优化和业务数据管理。 - 熟悉 Redis / Valkey、BullMQ 或类似队列系统，具备异步任务、重试机制、任务调度和后台处理经验。 - 熟悉 Docker 容器化开发与部署流程。 - 熟悉 Nx、Turborepo 或同类大型 TypeScript Monorepo 的工程组织方式。 - 具备较强的问题分析能力，能够独立定位复杂系统中的链路问题、数据问题和性能问题。 - 具备完整产品开发与交付经验，能够在不确定需求下做出可靠的工程判断。 Requirements - Strong proficiency in TypeScript, React, and Next.js, with experience building complete web applications. - Strong proficiency in Node.js, with solid experience designing and building API services. - Experience with Hono, Express, or similar Node.js service frameworks. - Good understanding of AI Agent engineering concepts, including Agent Loop, tool calling, task orchestration, context management, tool execution, state tracking, and result persistence. - Strong experience with PostgreSQL and Prisma for data modeling, query optimization, and business data management. - Experience with Redis / Valkey, BullMQ, or similar queue and caching systems, including async jobs, retry mechanisms, scheduling, and background processing. - Familiarity with Docker-based development and deployment workflows. - Experience with Nx, Turborepo, or similar large-scale TypeScript Monorepo setups. - Strong problem-solving skills, with the ability to independently debug complex system, data, and execution-flow issues. - Experience delivering complete product features in real-world production environments. Benefits - 加分项 - 有 Mastra、LangChain、LlamaIndex、AutoGen、CrewAI 或其他 Agent 编排框架经验。 - 有 RAG、向量检索、Embedding、知识库、LLM 工具调用或多模态生成系统经验。 - 熟悉 FastAPI、Flask，或有 Python LLM 应用开发经验。 - 熟悉 NestJS、Fastify、Koa、tRPC、GraphQL、WebSocket 等 Node.js 生态技术。 - 有 AWS 或其他云服务部署、运维、监控经验。 - 有 CI/CD、系统监控、日志追踪、性能分析、错误告警和生产稳定性建设经验。 - 参与过高并发、大规模用户系统或复杂后台任务系统的设计与开发。 - 熟悉 AI 产品中的模型路由、成本控制、生成任务状态管理、失败重试和结果一致性设计。 - 有从 0 到 1 搭建复杂 Web 产品、AI 产品或平台型产品的经验。

• Design, develop, and maintain Java-based applications using Spring Boot & Spring Security. • Work with relational databases (e.g., MySQL, PostgreSQL, Oracle) and optimize queries. • (Preferred) Experience with Camunda BPM for workflow automation. • Develop and integrate RESTful APIs and microservices. • Knowledge of JavaScript frameworks (React) for front-end integration. • Implement best practices for code quality, testing (JUnit, Mockito), and CI/CD pipelines. • Troubleshoot, debug, and optimize application performance. • Collaborate with DevOps teams for deployment and monitoring. • Participate in Agile/Scrum processes (sprints, stand-ups, retrospectives).