IA工程师
IA Engineer
关于我们的团队
Coderio 为全球公司设计和交付可扩展的数字解决方案。我们结合强大的技术专长与产品思维，从头到尾领导复杂的软件项目。我们与国际客户合作，重视自主性和清晰的沟通，并通过技术卓越建立长期合作关系。
🌍 更多信息：http://coderio.com
这是一个高影响力的工程技术岗位。我们正在寻找一名 AI 工程师加入我们的 AI 工程核心计划。你将在后端工程、云平台和应用 AI 的交汇点工作，构建共享的 AI 基础设施，帮助软件开发人员和产品团队安全、可观测且高效地采用生成式 AI。你的主要任务是设计、构建和运营可在整个组织中复用的 AI 能力、LLM 网关、模型路由、评估框架和防护机制。
这是一个注重执行和工程驱动的岗位。你将负责设计、基准测试和将生产级 AI 能力和代理流程直接部署到内部平台和软件生态系统中。
你在这个岗位上将承担的职责（Responsibilities）
- 共享 AI 基础设施：设计、实现并运营被多个工程和产品团队采用的生产级、可复用的 AI 能力和服务。
- LLM 基础设施与网关：构建和演进 LLM 网关、代理、模型路由机制、提示/上下文策略和代理流程（例如 LangGraph、PydanticAI、MCP）。
- 评估与可观测性：设计评估框架（黄金数据集、LLM 作为评判者）、防护机制和可观测性管道，以衡量任务成功率、延迟、安全性和 token 成本。
- 工程标准与最佳实践：定义组织内生产 AI 采用的标准，包括自动化测试、版本控制、上下文隔离和事件响应。
- 端到端交付：从问题定义和架构设计到实现、部署、监控和持续迭代，全程负责交付。
- 自动化与 DevEx：识别高影响力的机会，通过实施内部工具、脚本和智能流程来消除重复性手动工作，从而提升开发者效率。
要求
- 软件与 AI 工程基础：在软件工程、AI 工程或 ML 工程领域有高级经验（通常为 5 年以上），能够交付和运营生产级系统。
查看英文原文
About Us
Coderio designs and delivers scalable digital solutions for global companies. We combine strong technical expertise with a product mindset to lead complex software initiatives end-to-end. We work with international clients, value autonomy and clear communication, and build long-term partnerships through technical excellence.
🌍 More information: http://coderio.com
This is a high-impact technical role. We are looking for a AI Engineer to join our AI Engineering Core initiatives. You will operate at the intersection of backend engineering, cloud platforms, and applied AI, building shared AI foundations that help software developers and product teams adopt Generative AI safely, observably, and efficiently. Your primary mission is to design, build, and operate reusable AI capabilities, LLM gateways, model routing, evaluation frameworks, and guardrails across the organization.
This is a hands-on execution and engineering-driven role. You are responsible for designing, benchmarking, and deploying production-grade AI capabilities and agentic workflows directly into internal platforms and software ecosystems.
What To Expect In This Role (Responsibilities)
- Shared AI Foundations: Design, implement, and operate production-grade, reusable AI capabilities and services adopted by multiple engineering and product teams.
- LLM Infrastructure & Gateways: Build and evolve LLM gateways, proxies, model routing mechanisms, prompt/context strategies, and agentic workflows (e.g., LangGraph, PydanticAI, MCP).
- Evaluations & Observability: Design evaluation frameworks (golden sets, LLM-as-a-judge), guardrails, and observability pipelines to measure task success, latency, security, and token costs.
- Engineering Standards & Best Practices: Define standards for production AI adoption across the organization, including automated testing, versioning, context segregation, and incident response.
- End-to-End Delivery: Own delivery end-to-end—from problem framing and architectural design through implementation, deployment, monitoring, and continuous iteration.
- Automation & DevEx: Identify high-impact opportunities to eliminate repetitive manual work by implementing internal tools, scripts, and intelligent workflows that boost developer velocity.
Requirements
- Software & AI Engineering Foundation: Senior-level experience (typically 5+ years) delivering and operating production-grade systems in Software Engineering, AI Engineering, or ML Engineering.
- Development Skills: Advanced hands-on proficiency in Python, RESTful/async APIs, microservices, and cloud services (AWS or GCP).
- GenAI & Agentic Systems: Proven experience building reliable applications using LLMs, RAG pipelines, agent orchestration (e.g., LangGraph, CrewAI), and Model Context Protocol (MCP).
- LLM Infrastructure & Evals: Hands-on experience with LLM proxies/gateways, model routing, evaluation harnesses, and AI observability tools (e.g., LangSmith, Datadog, Logfire).
- Architecture & Trade-offs: Ability to make sound architectural decisions balancing quality, latency, reliability, security, privacy, scalability, and cost.
- Language & Communication: Advanced English proficiency (mandatory) with clear communication skills to collaborate effectively with cross-functional technical stakeholders.
Nice to Have
- Experience with container orchestration (Docker, Kubernetes) and Infrastructure-as-Code (Terraform) in cloud environments.
- Experience building, scaling, or contributing to Internal Developer Platforms (IDP) or developer tooling.
- Background in prompt engineering optimization, fine-tuning open-source models, or custom vector database indexing.
Benefits
- High-impact, strategic role driving shared AI foundations and internal developer adoption.
- Collaborative international environment with senior technical leadership.
- High autonomy to research, prototype, and implement cutting-edge GenAI workflows.
- Long-term 100% remote engagement with competitive compensation and growth opportunities.
Why Join Coderio?
At Coderio, we value talent and technical excellence. We are passionate about modern engineering, high autonomy, and building solutions that make a real difference. We offer an inclusive and challenging environment where innovation is encouraged and technical leadership is valued. If you are eager to research and deploy next-generation AI solutions that elevate engineering teams, apply now.