平头哥平头哥-AI Agent 应用开发工程师-上海
社招全职3年以上技术类-开发地点：上海状态：招聘
任职要求
1. 计算机相关专业背景，3 年以上软件开发经验，具备 1 个及以上 LLM/Agent 项目落地经验 2. 编程能力强，熟练 Python（优先）或 TypeScript，掌握工程化实践（模块化、单元测试、CI/CD、容器化） 3. 熟悉 PyTorch 训练/微调与推理基本流程；能基于 vLLM 部署与调优（PagedAttention、KV Cache、并行与批处理） 4. 理解 CUDA 基础与 GPU 性能调优思路（显存/带宽/并发），会用 Nsight/Profiler 定位瓶颈，能与框架协同优化 5. 熟悉 openWebUI 的部署与模型接入，能做定制化改造；熟悉 Cursor/Code 类 AI 辅助工具，并能在研发团队内部形成高效开发工作流 6. 掌握 Agent/RAG 常用框架与模式：LangChain/LangGraph、LlamaIndex、Function/Tool Callin…
登录查看完整任职要求
微信扫码，1秒登录
工作职责
1. 设计与开发面向业务的 Agent 应用与多智能体流程：任务规划、工具调用、记忆、RAG 检索、反思与自我修复 2. 搭建与优化 LLM 推理与服务：基于 vLLM/TensorRT-LLM/Triton 部署模型，提供 OpenAI 兼容 API，优化吞吐、时延与成本 3. 集成与定制 openWebUI 等前端/运维界面，结合企业需求进行二次开发；熟练使用 Cursor 等 AI 编程工具提升研发效率 4. 构建知识与数据通道：Embedding、向量库（Milvus/FAISS/Weaviate 等）、检索重排、权限与更新策略 5. 建立评测与观测：任务成功率、一次通过率、P95 时延、成本监控、A/B 测试、内容安全与越狱防护；沉淀最佳实践与文档 6. 跨团队协作与敏捷交付：从 PRD/需求澄清到 MVP 上线，度量指标驱动迭代，确保按期交付与质量
包括英文材料
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.
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.
TypeScript+
https://www.youtube.com/watch?v=JHEB7RhJG1Y
Master TypeScript from basics to advanced concepts through hands-on tutorials covering type annotations, generics, data fetching, Zod library, and more, with practical challenges for effective real-world application.
CI+
https://www.ibm.com/cn-zh/think/topics/continuous-integration
持续集成 (CI) 是一种软件开发实践，开发人员在整个开发周期中会定期将新的代码和代码变更集成到中央代码存储库中。它是 DevOps 和敏捷方法的关键组成部分。
https://www.youtube.com/watch?v=42UP1fxi2SY
CD+
https://www.redhat.com/zh-cn/topics/devops/what-is-ci-cd
CI/CD 是持续集成和持续交付/部署的缩写，旨在简化并加快软件开发生命周期。
https://www.youtube.com/watch?v=R8_veQiYBjI&list=PLy7NrYWoggjzSIlwxeBbcgfAdYoxCIrM2
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.
vLLM+
https://www.newline.co/@zaoyang/ultimate-guide-to-vllm--aad8b65d
vLLM is a framework designed to make large language models faster, more efficient, and better suited for production environments.
https://www.youtube.com/watch?v=Ju2FrqIrdx0
vLLM is a cutting-edge serving engine designed for large language models (LLMs), offering unparalleled performance and efficiency for AI-driven applications.
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
CUDA+
https://developer.nvidia.com/blog/even-easier-introduction-cuda/
This post is a super simple introduction to CUDA, the popular parallel computing platform and programming model from NVIDIA.
https://www.youtube.com/watch?v=86FAWCzIe_4
Lean how to program with Nvidia CUDA and leverage GPUs for high-performance computing and deep learning.
性能调优+
https://goperf.dev/
The Go App Optimization Guide is a series of in-depth, technical articles for developers who want to get more performance out of their Go code without relying on guesswork or cargo cult patterns.
https://web.dev/learn/performance
This course is designed for those new to web performance, a vital aspect of the user experience.
https://www.ibm.com/think/insights/application-performance-optimization
Application performance is not just a simple concern for most organizations; it’s a critical factor in their business’s success.
https://www.oreilly.com/library/view/optimizing-java/9781492039259/
Performance tuning is an experimental science, but that doesn’t mean engineers should resort to guesswork and folklore to get the job done.
Nsight+
https://developer.nvidia.com/tools-tutorials
NVIDIA Nsight™ Developer tools are a suite of tools for building, profiling, and debugging accelerated applications.
https://www.youtube.com/watch?v=aQ1NYoRvp7o
Profile Python for AI and deep learning applications with NVIDIA's suite of Nsight Developer Tools.
https://www.youtube.com/watch?v=Iuy_RAvguBM
Join NVIDIA’s Jackson Marusarz for an introduction to NVIDIA Nsight Compute, a tool for in-depth analysis of CUDA kernel performance on GPUs.
RAG+
https://www.youtube.com/watch?v=sVcwVQRHIc8
Learn how to implement RAG (Retrieval Augmented Generation) from scratch, straight from a LangChain software engineer.
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.
还有更多 •••
相关职位
实习阿里云2026届
阿里云持续推进AI 技术深化战略布局， 围绕AI 和云计算的基础设施建设、AI基础模型平台、企业级AI应用方向构建核心场景。为此，我们正积极招募优秀人才： 1.AI Agent应用开发全流程工作，包括但不限于prompt工程、RAG优化、multi-Agent构建、流程编排等； 2.参与AI Agent产品的需求分析、技术选型、方案设计、用户体验提升等； 3.关注AI与大模型领域技术发展趋势，并灵活应用于项目中。
更新于 2025-06-17上海
社招3年以上国际业务开发
1. 负责服务端系统架构设计与开发、数据库设计 2. 负责功能模块的代码编写，独立完成单元测试与集成测试 3. 负责服务端接口开发及前后端联调 4. 负责编写软件开发过程所涉及的技术文档 5. 系统的部署、维护、优化及日常数据库管理 6. 参与AI Agent相关应用的服务端开发与集成
更新于 2025-12-01上海
社招系统开发
负责基于大模型构建可落地、可复用的 AI Agent 应用与服务，让模型从“能对话”进化为“能完成任务”。 1. 基于主流大模型（如 Qwen、DeepSeek、SenseNova 等）设计并开发 AI Agent，解决真实业务问题。 2. 负责 Agent 核心能力开发，包括 任务规划、工具/API 调用、记忆机制（RAG）与结果校验。 3. 使用 LangChain / LangGraph / AutoGen 等框架，构建 单 Agent 或多 Agent 协作流程。 4. 编写和优化 Prompt，持续提升 Agent 输出的 稳定性、准确性和可控性。 5. 将 Agent 能力封装为 API 或服务，集成到现有业务系统中，并关注 效果、成本与延迟。
更新于 2025-12-23北京|上海
社招3-6年技术类-开发
1、负责反洗钱以及合规面向智能化的风险识别，判断，审理的工程搭建，推动产品落地。 2、能够应用大模型或者智能体思维来推动业务或者产品能力创新，以及AI产品化表达能力； 3、深度参与智能化研发全流程，涵盖大模型数据生成、训练或微调、RAG以及实验部署等，推动智能化架构在反洗钱风控、合规场景的落地； 4、不断探索技术新领域，进行重点难点技术攻关工作。
更新于 2025-04-03上海