西门子AI Native 架构师(企业级 AI Agent 开发平台)
社招全职5-10年研发地点:深圳状态:招聘♡ 收藏
工作描述
汇报关系:本岗位向平台总架构师汇报,在总架构师的统筹与指导下,负责 AI 域领域架构设计、方案输出与落地推进,跨域方案需提交总架构师评审决策。 一、岗位名称 AI Native 架构师(企业级 AI Agent 开发平台) 二、岗位职责 1. AI Native 平台整体架构设计 在平台总架构师的指导下,负责 XAgent 企业级 AI Agent 开发平台的 AI Native 技术架构规划、设计与持续演进,建立可扩展、可复用、安全可靠的企业级 Agent 技术底座。 设计 AI 应用层、Agent Runtime、模型与上下文管理、Skill/Tool 执行层、知识检索、评测治理及云平台基础设施之间的分层架构和接口规范。 明确 AI Native 能力与传统云平台能力的职责边界,复用现有身份认证、多租户、数据库、计费、消息队列及云基础设施,避免重复建设。 结合工业企业及企业级应用需求,制定 AI 域内技术选型、架构原则、关键技术路线和中长期技术演进规划,方案提交总架构师参与整体平台技术路线评审。 2. Agent Runtime 与智能执行架构 在平台总架构师的指导下,设计 Agent 的任务规划、执行循环、状态管理、长任务运行、暂停恢复、重试、超时控制及异常恢复机制。 设计 Workflow、单 Agent、多 Agent 协作等不同执行模式,明确适用场景、执行约束和工程化边界。 建立统一的模型接入、模型路由、推理策略、上下文组装、记忆管理及工具调用架构。 设计 Skill/Tool 注册、发现、版本管理、执行协议、权限委托、运行隔离及结果校验机制,支持生态伙伴和第三方工具接入。 针对工业业务中对准确性、可追溯性及安全性的要求,设计 AI 推理与确定性业务逻辑、工业控制及人工审批之间的安全边界,相关跨模块集成方案同步总架构师。 3. AI 工程化、质量与安全治理 在平台总架构师的指导下,建立 AI Agent 评测体系,涵盖任务成功率、回答质量、工具调用准确性、执行稳定性、推理成本和响应延迟等指标;主导 AI 模型测试体系与 AI 应用能力验证平台设计,构建模型功能、精度、鲁棒性、对抗样本、分布漂移、版本对比的自动化测试能力;面向 Agent 应用场景搭建场景化测试集、回归用例、验收基准,实现模型、Agent 应用的自动化能力验证与版本准入门禁。 主导自有模型与领域模型工程体系设计,构建训练数据治理、预处理、SFT/LoRA 微调、模型蒸馏、量化、版本管理的端到端管线;基于 Transformer、残差网络(ResNet)、BN 批量归一化等深度学习底层原理,评审模型结构方案,评估模型能力边界、收敛特性、显存开销、推理延迟与潜在缺陷;打通训练管线产出模型到平台模型网关、Agent Runtime 的全链路交付,支撑平…
登录查看完整工作描述
微信扫码,1秒登录
包括英文材料
系统设计+
https://roadmap.sh/system-design
Everything you need to know about designing large scale systems.
https://www.youtube.com/watch?v=F2FmTdLtb_4
This complete system design tutorial covers scalability, reliability, data handling, and high-level architecture with clear explanations, real-world examples, and practical strategies.
AI agent+
https://www.ibm.com/think/ai-agents
Your one-stop resource for gaining in-depth knowledge and hands-on applications of AI agents.
消息队列+
https://www.youtube.com/watch?v=xErwDaOc-Gs
数据治理+
https://www.ibm.com/think/topics/data-governance
Data governance is the data management discipline that focuses on the quality, security and availability of an organization’s data.
https://www.youtube.com/watch?v=uPsUjKLHLAg
Building data fabric eliminates the technological complexities of data governance so users can connect to the right data at the right time, regardless of where it resides.
SFT+
https://cameronrwolfe.substack.com/p/understanding-and-using-supervised
Understanding how SFT works from the idea to a working implementation...
Transformer+
https://huggingface.co/learn/llm-course/en/chapter1/4
Breaking down how Large Language Models work, visualizing how data flows through.
https://poloclub.github.io/transformer-explainer/
An interactive visualization tool showing you how transformer models work in large language models (LLM) like GPT.
https://www.youtube.com/watch?v=wjZofJX0v4M
Breaking down how Large Language Models work, visualizing how data flows through.
深度学习+
https://d2l.ai/
Interactive deep learning book with code, math, and discussions.
Prompt+
https://cloud.google.com/vertex-ai/generative-ai/docs/learn/prompts/introduction-prompt-design
A prompt is a natural language request submitted to a language model to receive a response back.
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/prompt-engineering
These techniques aren't recommended for reasoning models like gpt-5 and o-series models.
https://www.youtube.com/watch?v=LWiMwhDZ9as
Learn and master the fundamentals of Prompt Engineering and LLMs with this 5-HOUR Prompt Engineering Crash Course!
缓存+
https://hackernoon.com/the-system-design-cheat-sheet-cache
The cache is a layer that stores a subset of data, typically the most frequently accessed or essential information, in a location quicker to access than its primary storage location.
https://www.youtube.com/watch?v=bP4BeUjNkXc
Caching strategies, Distributed Caching, Eviction Policies, Write-Through Cache and Least Recently Used (LRU) cache are all important terms when it comes to designing an efficient system with a caching layer.
https://www.youtube.com/watch?v=dGAgxozNWFE
高可用+
https://redis.io/blog/high-availability-architecture/
A high available architecture is when there are a number of different components, modules, or services that work together to maintain optimal performance, irrespective of peak-time loads.
https://www.ibm.com/think/topics/high-availability
High availability (HA) is a term that refers to a system’s ability to be accessible and reliable close to 100% of the time.
学历+
大模型+
https://www.youtube.com/watch?v=xZDB1naRUlk
You will build projects with LLMs that will enable you to create dynamic interfaces, interact with vast amounts of text data, and even empower LLMs with the capability to browse the internet for research papers.
https://www.youtube.com/watch?v=zjkBMFhNj_g
还有更多 •••
相关职位
社招5-10年
1. **经验要求** - 本科及以上学历,计算机或相关专业。 - 8年以上软件研发经验,具备复杂系统架构设计经验。 - 具备ToG行业项目经验(公安、政务或城市治理相关领域)
更新于 2026-03-25深圳
社招5-10年
1、具备AI Coding实战经验,提供GitHub/GitLab生产级代码(Java/TS优先),主导过完整项目的AI自动化重构,有提效数据支撑 2、熟悉ReAct、Plan-and-Execute
更新于 2026-03-25深圳
社招8年以上软件开发岗
1、计算机相关专业本科及以上学历,8年以上开发及复杂系统架构设计经验; 2、深入理解微服务、Service Mesh、Serverless等云原生架构理念,具备高并发、高可用场景的架构设计与调优经验,
更新于 2026-04-06北京