阿里云阿里云智能-AI Agent研发工程师-AI搜索-杭州
社招全职5年以上云智能集团地点:杭州状态:招聘
任职要求
1.职位要求 基础条件 ● 计算机科学、人工智能、软件工程或相关专业本科及以上学历。 ● 5-8 年以上搜索、推荐、NLP、大模型应用、AI Agent 或大规模分布式系统核心研发经验,条件优秀者可放宽年限要求。 ● 具备极强的工程落地能力,精通 Python、Go、Java、C++ 中至少一到两门语言。 ● 有复杂系统架构设计经验,能够从业务目标出发设计可扩展、可维护、可评估的技术方案。 核心技术能力 ● Agent 与 LLM 应用架构:熟悉 AI Agent 的核心机制,包括任务规划、工具调用、工作流编排、记忆管理、上下文管理、多 Agent 协作等;有 LangChain、LlamaIndex、AutoGen、LangGraph、CrewAI 或自研 Agent Framework 的实战经验。 ● RAG 与 Agentic Search:深入理解 RAG、Hybrid Search、Query Rewriting、Reranking、Context Compression、GraphRAG、多跳检索、Deep Search 等技术,有复杂知识问答或企业智能搜索系统落地经验。 ● 搜索与检索系统:熟悉 Elasticsearch、Lucene、Solr、Milvus、Qdrant、Weaviate、Faiss 等搜索或向量检索系统,理解倒排索引、向量索引、召回排序、相关性优化与大规模集群调优。 ● 大模型工程化:熟悉 LLM 基础原理与应用接口,了解 Prompt Engineering、Function Calling / Tool Calling、SFT、模型路由、推理加速、上下文管理、缓存与成本优化等工程实践。 ● 评测与可观测性:理解 Agent / RAG 系统的评测方法,能够设计离线评测集、在线反馈机制、A/B 实验、自动化评测Pipeline,并基于数据持续改进系统效果。 ● 分布式与云原生:熟悉微服务架构、消息队列、任务调度、缓…
登录查看完整任职要求
微信扫码,1秒登录
工作职责
1. 作为核心技术骨干,参与企业级 Agentic Search / 通用 Agent 平台的架构设计、技术选型与核心链路研发。 ● 设计并演进 Agent 的任务规划、步骤分解、工具调用、状态管理、上下文管理、记忆机制与执行调度框架。 ● 构建面向复杂问题的 Deep Search / Deep Research 能力,使系统具备多轮检索、多步推理、动态改写查询、反思校验与结果综合能力。 ● 推动 Agent 系统从 Demo 形态走向生产级系统,重点解决稳定性、可观测性、可控性、延迟、成本与评测闭环问题。 2. RAG 与复杂知识检索技术攻坚 ● 深入优化 RAG 系统架构,解决海量异构企业文档、知识库、业务数据中的解析、切分、索引、召回、重排与答案生成问题。 ● 构建面向 Agent 的检索基础设施,包括混合检索、语义召回、结构化查询、知识图谱检索、GraphRAG、多跳检索与上下文压缩能力。 ● 设计高质量的 Query Understanding / Query Rewriting / Intent Routing 机制,提升 Agent 在复杂任务中的检索精度与推理效率。 ● 解决长上下文、长链路任务中的信息丢失、幻觉控制、引用溯源、事实一致性与结果可信问题。 3. Agent 工程化与系统能力建设 ● 负责 Agent Runtime、Workflow Engine、Tool Registry、Memory Store、Prompt / Policy 管理、任务队列等关键模块的设计与实现。 ● 建设面向生产环境的 Agent 可观测体系,包括调用链追踪、步骤日志、失败恢复、成本监控、质量评估与在线反馈机制。 ● 优化 LLM 调用链路的性能与成本,包括模型路由、缓存、并发控制、流式输出、推理加速、上下文裁剪与多模型协同。 ● 与算法、产品、业务团队协作,将 Agent 能力落地到企业搜索、知识问答、业务助手、自动分析、智能运营等真实场景。 4. 搜索、模型与多模态能力融合 ● 构建和优化混合检索架构,实现全文检索、向量检索、结构化检索、知识图谱与业务规则的深度融合。 ● 推动排序、重排、语义匹配、跨模态理解等模型能力在 Agentic Search 场景中的工程化落地。 ● 支持文本、表格、图片、PDF、Word、网页、业务系统数据等多源异构信息的统一理解、索引与调用。 ● 持续提升系统在准确率、召回率、推理深度、响应时延、用户满意度等维度的综合表现。 5. 技术引领与团队赋能 ● 解决 Agent 系统研发过程中的复杂工程问题,包括长任务稳定性、工具调用失败恢复、复杂上下文管理、评测体系建设、线上质量退化定位等。 ● 建立高质量的工程标准,通过架构评审、Code Review、技术分享与结对编程,提升团队在 Agent、RAG、搜索和大模型工程方向的整体技术深度。 ● 持续跟踪 Agentic AI、Deep Research、GraphRAG、多模态 Agent、LLM Evaluation、模型推理优化等前沿技术,并推动其在业务中的合理落地。
包括英文材料
学历+
NLP+
https://www.youtube.com/watch?v=fNxaJsNG3-s&list=PLQY2H8rRoyvzDbLUZkbudP-MFQZwNmU4S
Welcome to Zero to Hero for Natural Language Processing using TensorFlow!
https://www.youtube.com/watch?v=R-AG4-qZs1A&list=PLeo1K3hjS3uuvuAXhYjV2lMEShq2UYSwX
Natural Language Processing tutorial for beginners series in Python.
https://www.youtube.com/watch?v=rmVRLeJRkl4&list=PLoROMvodv4rMFqRtEuo6SGjY4XbRIVRd4
The foundations of the effective modern methods for deep learning applied to NLP.
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
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.
分布式系统+
https://www.distributedsystemscourse.com/
The home page of a free online class in distributed systems.
https://www.youtube.com/watch?v=7VbL89mKK3M&list=PLOE1GTZ5ouRPbpTnrZ3Wqjamfwn_Q5Y9A
Python+
https://liaoxuefeng.com/books/python/introduction/index.html
中文,免费,零起点,完整示例,基于最新的Python 3版本。
https://www.learnpython.org/
a free interactive Python tutorial for people who want to learn Python, fast.
https://www.youtube.com/watch?v=K5KVEU3aaeQ
Master Python from scratch 🚀 No fluff—just clear, practical coding skills to kickstart your journey!
https://www.youtube.com/watch?v=rfscVS0vtbw
This course will give you a full introduction into all of the core concepts in python.
Go+
https://www.youtube.com/watch?v=8uiZC0l4Ajw
学习Golang的完整教程!从开始到结束不到一个小时,包括如何在Go中构建API的完整演示。没有多余的内容,只有你需要知道的知识。
Java+
https://www.youtube.com/watch?v=eIrMbAQSU34
Master Java – a must-have language for software development, Android apps, and more! ☕️ This beginner-friendly course takes you from basics to real coding skills.
C+++
https://www.learncpp.com/
LearnCpp.com is a free website devoted to teaching you how to program in modern C++.
https://www.youtube.com/watch?v=ZzaPdXTrSb8
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.
LangChain+
https://python.langchain.com/docs/tutorials/
New to LangChain or LLM app development in general? Read this material to quickly get up and running building your first applications.
https://www.freecodecamp.org/news/beginners-guide-to-langchain/
LangChain is a popular framework for creating LLM-powered apps.
LlamaIndex+
https://developers.llamaindex.ai/python/framework/getting_started/starter_example/
This tutorial will show you how to get started building agents with LlamaIndex.
https://www.ibm.com/think/tutorials/llamaindex-rag
LlamaIndex is a powerful open source framework that simplifies the process of building RAG pipelines.
AutoGen+
https://microsoft.github.io/autogen/0.2/docs/Getting-Started/
AutoGen is an open-source programming framework for building AI agents and facilitating cooperation among multiple agents to solve tasks.
https://www.youtube.com/watch?v=JmjxwTEJSE8
Whether you know everything there to AI Agents or are a complete beginner, I believe there is something to learn here.
开发框架+
[英文] Understanding Modern Development Frameworks: A Guide for Developers and Technical Decision-makers
https://www.freecodecamp.org/news/understanding-modern-development-frameworks-guide-for-devs/
RAG+
https://www.youtube.com/watch?v=sVcwVQRHIc8
Learn how to implement RAG (Retrieval Augmented Generation) from scratch, straight from a LangChain software engineer.
信息检索+
https://nlp.stanford.edu/IR-book/information-retrieval-book.html
Christopher D. Manning, Prabhakar Raghavan and Hinrich Schütze, Introduction to Information Retrieval, Cambridge University Press. 2008.
ElasticSearch+
https://www.youtube.com/watch?v=a4HBKEda_F8
Learn about Elasticsearch with this comprehensive course designed for beginners, featuring both theoretical concepts and hands-on applications using Python (though applicable to any programming language). The course is structured in two parts: first covering essential Elasticsearch fundamentals including index management, document storage, text analysis, pipeline creation, search functionality, and advanced features like semantic search and embeddings; followed by a practical section where you'll build a real-world website using Elasticsearch as a search engine, working with the Astronomy Picture of the Day (APOD) dataset to implement features such as data cleaning pipelines, tokenization, pagination, and aggregations.
还有更多 •••