平安科技AI智能体架构师
社招全职5年以上计算机网络技术类地点：深圳状态：招聘
任职要求
1、5年以上Java项目开发经验，一年以上架构经验，熟悉Spring、SpringMVC、myBatis、sphinx/lucene、redis、Zookeeper、elasticsearch等开源框架，能了解到它的原理和机制； 2、熟悉Mysql、postgresql等数据库；熟悉LINUX操作系统, 对NOSQL技术有一定熟悉； 3、熟悉分布式系统的设计和应用，熟悉分布式缓存、消息、搜索等机制；能对分布式常用技术进行合理应用，解决问题； 4、熟悉大规模系统的负载均衡、缓存、网络存储、网络安全、数据库高可用设计及性能评估机制 5、有AI研发经验，熟悉DeepSeek、Qwen等模型搭建，熟悉dify等系统，对AI应用架构有深入理解。 6、精通PyTorch/TensorFlow生态及底层机制。
工作职责
作为AI助手类的技术架构师，工作职责包括且不限于 1. 规划AI系统技术架构，设计包含算法、数据流、硬件资源等的整体蓝图； 2、探索AI前沿技术，跟踪前沿技术（如生成式AI、多模态模型），探索创新应用方向； 3、协同团队进行系统概要设计、开发框架搭建、代码评审等； 4、指导开发团队实现技术方案，推动AI技术在实际业务中的价值转化； 5、主导系统技术选型、技术的可行性评估、技术难点攻关 、问题分析及系统调优等； 3、参与智能体系统的开发与实现，确保系统在复杂环境下的稳定性和高效性，配合产品团队，将智能体技术应用于实际场景，推动技术落地。 4、有自主意识和创业精神，目标导向、自我驱动，团队协作能力强，有良好的沟通能力、执行力和抗压力。
包括英文材料
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.
Spring+
https://liaoxuefeng.com/books/java/spring/index.html
Spring是一个支持快速开发Java EE应用程序的框架。它提供了一系列底层容器和基础设施，并可以和大量常用的开源框架无缝集成，可以说是开发Java EE应用程序的必备。
https://spring.io/guides/gs/rest-service
https://spring.io/quickstart
Level up your Java code and explore what Spring can do for you.
Spring Web MVC+
https://spring.io/guides/gs/serving-web-content
This guide walks you through the process of creating a “Hello, World” web site with Spring.
[英文] Spring MVC Series
https://www.baeldung.com/spring-mvc
Spring MVC provides tools driving both typical web applications as well as REST APIs.
MyBatis+
https://mybatis.org/mybatis-3/getting-started.html
https://www.baeldung.com/mybatis
MyBatis is an open source persistence framework which simplifies the implementation of database access in Java applications.
Redis+
[英文] Developer Hub
https://redis.io/dev/
Get all the tutorials, learning paths, and more you need to start building—fast.
https://www.runoob.com/redis/redis-tutorial.html
REmote DIctionary Server(Redis) 是一个由 Salvatore Sanfilippo 写的 key-value 存储系统，是跨平台的非关系型数据库。
https://www.youtube.com/watch?v=jgpVdJB2sKQ
In this video I will be covering Redis in depth from how to install it, what commands you can use, all the way to how to use it in a real world project.
ZooKeeper+
https://kubernetes.io/docs/tutorials/stateful-application/zookeeper/
This tutorial demonstrates running Apache Zookeeper on Kubernetes using StatefulSets, PodDisruptionBudgets, and PodAntiAffinity.
https://www.baeldung.com/java-zookeeper
Apache ZooKeeper is a distributed coordination service which eases the development of distributed applications.
[英文] Zookeeper Tutorial
https://www.tutorialspoint.com/zookeeper/index.htm
ZooKeeper is a distributed co-ordination service to manage large set of hosts.
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.
MySQL+
https://juejin.cn/post/7190306988939542585
这是一篇 MySQL 通关一篇过硬核经验学习路线，包括数据库相关知识，SQL语句的使用，数据库约束，设计等。
[英文] MySQL Tutorial
https://www.mysqltutorial.org/
your go-to resource for mastering MySQL in a fast, easy, and enjoyable way.
https://www.youtube.com/watch?v=5OdVJbNCSso
MySQL SQL tutorial for beginners
https://www.youtube.com/watch?v=7S_tz1z_5bA
This beginner-friendly course teaches you SQL from scratch.
PostgreSQL+
[英文] PostgreSQL Tutorial
https://neon.com/postgresql/tutorial
This PostgreSQL tutorial helps you quickly understand PostgreSQL.
[英文] PostgreSQL Tutorial
https://www.pgtutorial.com/
This PostgreSQL tutorial will teach you about PostgreSQL from beginner to advanced.
https://www.youtube.com/watch?v=qw--VYLpxG4
It is the most advanced open source database system widely used to build back-end systems.
https://www.youtube.com/watch?v=SpfIwlAYaKk
Learn PostgreSQL, one of the world's most advanced and robust open-source relational database systems.
Linux+
https://ryanstutorials.net/linuxtutorial/
Ok, so you want to learn how to use the Bash command line interface (terminal) on Unix/Linux.
https://ubuntu.com/tutorials/command-line-for-beginners
The Linux command line is a text interface to your computer.
https://www.youtube.com/watch?v=6WatcfENsOU
In this Linux crash course, you will learn the fundamental skills and tools you need to become a proficient Linux system administrator.
https://www.youtube.com/watch?v=v392lEyM29A
Never fear the command line again, make it fear you.
https://www.youtube.com/watch?v=ZtqBQ68cfJc
NoSQL+
https://nosql-database.org/
Everything about NoSQL Systems – Types, Benefits, and Real-World Uses
https://piaosanlang.gitbooks.io/mongodb/content/section1.1.html
NoSQL(NoSQL = Not Only SQL )，即"不仅仅是SQL"，指的是非关系型的数据库。是对不同于传统的关系型数据库管理系统的统称。
https://www.youtube.com/watch?v=0buKQHokLK8
NoSQL databases can operate in multiple modes: as key-value store, document store or wide column store.
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
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.
PyTorch+
https://datawhalechina.github.io/thorough-pytorch/
PyTorch是利用深度学习进行数据科学研究的重要工具，在灵活性、可读性和性能上都具备相当的优势，近年来已成为学术界实现深度学习算法最常用的框架。
https://www.youtube.com/watch?v=V_xro1bcAuA
Learn PyTorch for deep learning in this comprehensive course for beginners. PyTorch is a machine learning framework written in Python.
TensorFlow+
https://www.youtube.com/watch?v=tpCFfeUEGs8
Ready to learn the fundamentals of TensorFlow and deep learning with Python? Well, you’ve come to the right place.
https://www.youtube.com/watch?v=ZUKz4125WNI
This part continues right where part one left off so get that Google Colab window open and get ready to write plenty more TensorFlow code.
相关职位
社招4年以上研发类
1、负责大语言模型和多模态大模型的智能体算法构建，结合高质量语料库、小工具、检索等能力，构建复杂专业领域的大模型智能体系统； 2、提升大模型自主工具调用及工具创造能力，增强Agent在移动机器人场景下的综合能力； 3、负责具身AI模型相关研发工作，聚焦垂直领域大模型预训练和领域精调，包括模型架构、多模态模型预训练方法、高效微调、模型评估及迭代等，支持行业内应用落地； 4、负责设计、构建和优化AI智能体及其应用产品，设计并实现基于大模型的智能体架构，支撑AI智能体构建； 5、解决项目执行过程中遇到的技术难题，特别是与大模型相关的挑战。
更新于 2025-02-25
社招A207557
1、负责设计、构建和优化AI智能体及其应用产品，设计基于大模型的智能体架构，支撑AI智能体构建； 2、负责设计多智能体协同架构，支撑多智能体协同解决复杂任务； 3、对现有的智能体平台进行评估，识别改进的机会，提升开发效率和平台可扩展性； 4、解决项目执行过程中遇到的技术难题，特别是与大模型相关的挑战； 5、支持售前工作，负责与客户沟通AI智能体方案。
更新于 2025-02-14
社招A238387B
1、负责设计、构建和优化AI智能体及其应用产品，设计基于大模型的智能体架构，支撑AI智能体构建； 2、负责设计多智能体协同架构，支撑多智能体协同解决复杂任务； 3、对现有的智能体平台进行评估，识别改进的机会，提升开发效率和平台可扩展性； 4、解决项目执行过程中遇到的技术难题，特别是与大模型相关的挑战； 5、支持售前工作，负责与客户沟通AI智能体方案。
更新于 2025-02-14
社招5年以上技术开发类
职位职责（Responsibilities） 1.主导云端智能 Agent 的系统架构设计与核心模块开发，涵盖对话状态管理、意图推理、上下文建模、响应生成、工具调用（Tool Calling）及多模态决策逻辑。 2.设计并实现高可用、低延迟、可扩展的微服务架构，支撑百万级 QPS 的并发对话请求，保障系统稳定性与容灾能力。 推动大语言模型（LLM）在云端 Agent 中的深度集成，包括 Prompt 工程优化、上下文压缩、推理加速、缓存策略、Agent 编排框架等关键技术落地。 3.深入分析系统性能瓶颈，优化从请求接入、上下文检索、模型推理到响应生成的全链路延迟，持续提升 TTFB（首字节时间）与用户体验。 探索基于 RAG、Function Calling、Agent 记忆机制、个性化建模等前沿技术的工程实现路径，推动创新功能产品化。 4.与算法、产品、运维团队紧密协作，完成从技术预研、灰度发布到全量上线的全周期交付。
更新于 2025-10-11