AI平台工程师
AI Platform Engineer
### **关于 Starburst**
Starburst 通过为组织提供安全、受控的数据访问，实现大规模的企业智能。针对分布式数据环境构建，Starburst 帮助企业无需传统数据整合的成本和复杂性即可推动 AI 和分析。凭借 Trino 和 Apache Iceberg 等开放标准，Starburst 使组织能够获得完整的企业上下文信任访问，同时帮助其避免供应商锁定。领先的全球企业信赖 Starburst 来驱动 AI、分析和企业智能。了解更多信息，请访问 [starburst.ai](http://starburst.ai)。
##### 关于团队
我们为 Starburst 的产品（包括 AIDA）构建 AI 层。我们设计代理，让用户可以用自然语言提问并获得基于实际数据的准确答案。我们在一家企业公司内部以初创公司的速度运作，每周发布并衡量结果。这是团队中第一位专门的平台工程职位。
##### 职位概述
你将构建多个产品团队更快使用的共享开发基础组件，实现 Python/JVM 边界上的清晰抽象。这个职位是放大器：而不是直接构建产品功能，你将构建平台、SDK 和工具，使团队中的每位工程师都能更快交付。
你将负责 Starburst 中代理开发的开发者体验，从 0 到 1 构建并跨团队扩展。你的工作成效由其他工程师的速度来衡量，而非你自己的功能产出。
##### 在 Starburst 担任 AI 平台工程师，你将：
- 设计并构建代理开发 SDK，抽象常见模式（工具注册、上下文管理、评估钩子、提示管理）
- 在 Python（AI 生态系统）和 JVM（Starburst 平台）之间建立语言桥梁，确保类型安全、错误传播和边界上的可观测性
- 创建开发者工具：本地开发环境、调试工具、测试框架、CI 集成
- 定义并维护 AI 层与 Starburst 平台之间的 API 协议
- 构建共享基础设施：模型网关、可观测性管道、实验框架
- 开发跨多个产品的通用、与产品无关的组件
- 除了功能交付之外，还负责平台健康状况：性能、可靠性、开发者体验
##### 我们寻找的一些特质：
- 5 年以上软件工程经验，具有
查看英文原文
### **About Starburst**
Starburst delivers enterprise intelligence at scale by giving organizations secure, governed access to all their data, wherever it lives. Built for distributed data environments, Starburst helps enterprises power AI and analytics without the cost and complexity of traditional data consolidation. With open standards including Trino and Apache Iceberg, Starburst enables trusted access to complete enterprise context while helping organizations avoid vendor lock-in. Leading global enterprises trust Starburst to fuel AI, analytics, and enterprise intelligence. Learn more at [starburst.ai](http://starburst.ai).
##### About the Team
We build the AI layer for Starburst's products, including AIDA. We design agents that let users ask questions in natural language and get accurate, grounded answers backed by their actual data. We operate with startup speed inside an enterprise company, shipping weekly and measuring results. This is the first dedicated platform engineering hire on the team.
##### Role Summary
You will build the shared development primitives that make multiple product teams faster, with clean abstractions across the Python/JVM boundary. This role is a force multiplier: instead of building product features directly, you build the platform, SDK, and tooling that enables every other engineer on the team to ship faster.
You will own the developer experience for agent development at Starburst, building from 0 to 1 and scaling across teams. Your work is measured by other engineers' velocity, not your own feature output.
##### As an AI Platform Engineer at Starburst, you will:
- Design and build an agent development SDK that abstracts common patterns (tool registration, context management, evaluation hooks, prompt management)
- Build the language bridge between Python (AI ecosystem) and JVM (Starburst platform) with type safety, error propagation, and observability across the boundary
- Create developer tooling: local development environments, debugging tools, test harnesses, CI integration
- Define and maintain API contracts between the AI layer and the Starburst platform
- Build shared infrastructure: model gateway, observability pipeline, experiment framework
- Develop unified, product-agnostic components used across multiple products
- Own platform health beyond feature delivery: performance, reliability, developer ergonomics
##### Some of the things that we look for:
- 5+ years of software engineering experience, with at least 2 years building platform, infrastructure, or developer tooling
- Proficiency in both Python and JVM languages (Java or Kotlin)
- Experience designing APIs and SDKs consumed by other engineering teams
- Strong distributed systems fundamentals: RPC, serialization, error handling, observability
- Experience with containerization, CI/CD pipelines, and cloud infrastructure (AWS preferred)
- Track record of building tools that measurably improve other engineers' velocity
##### Preferred Qualifications
- Experience with LLM integration patterns: model APIs, token management, streaming, tool use
- Experience with cross-language interop (gRPC, FFI, language bridges)
- Open-source contributions to developer tooling or infrastructure projects
- Familiarity with A/B testing frameworks and experiment infrastructure
- Experience supporting both research and production workloads on the same platform
- Java agent framework experience (LangChain4j)
- **Ability to Travel**: This role will require 25% in-person travel for purposes including but not limited to new hire onboarding, team and department offsites, customer engagements, and other company events. Actual travel expectations may vary by role and business needs.
### **Build your career at Starburst**
All-Stars have the opportunity and freedom to realize their true potential. By building alongside top talent, we’re empowered to take ownership of our careers and drive meaningful change. Anchored in industry-proven technology and unprecedented success, All-Stars are taking on the challenge everyday to disrupt our industry – and the future.
Our global workforce is supported by a competitive Total Rewards program that reflects our commitment to a rewarding and supportive work environment. This includes a variety of benefits like competitive pay, attractive stock grants, flexible paid time off, and more.
We are committed to fostering an intentional, inclusive, and diverse culture that drives deep engagement, authentic belonging, and an exceptional All-Star experience. We believe that diversity of thought, perspective, background and experience will enable us to own what we do, drive our success and empower our All-Stars to show up authentically.
Starburst provides equal employment opportunities to all employees and applicants for employment and prohibits discrimination and harassment of any type without regard to race, color, religion, age, sex, national origin, disability status, genetics, protected veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by federal, state
or local laws.