阿里云阿里云智能-大模型推理优化专家/高级专家-北京/上海/深圳/杭州
社招全职5年以上云智能集团地点：北京 | 深圳 | 杭州 | 上海状态：招聘
任职要求
1. 主导大模型推理全链路优化：从计算图优化、算子融合到显存管理，构建面向Transformer架构的极致优化方案 2. 构建分布式推理引擎：设计模型并行、流水线并行、张量并行混合调度策略，支撑千卡集群的线性扩展能力 3. 计算机体系结构/算法优化双重功底：精通CUDA/Triton编程，能进行kernel级优化；熟悉TVM/MLIR/XLA等编译框架 4. 实战经验：具有LLaMA、GPT、GLM等百亿级模型优化经验，熟悉FlashAttention/PagedAttention等关键技术 5. 全栈优化：掌握从算法改进（MoE/混合专家系统）、框架调优（vLLM/DeepSpeed）到硬件协同设计的完整技术链条 6. 性能调优：能通过nsight systems等工具进行端到端性能分析，具备将理论算力转化为实际吞吐的杀手级能力
工作职责
1.负责主流大模型（DeepSeek、通义、LLaMA等）的全栈性能优化，涵盖模型架构优化、训练/推理框架调优及底层算子优化，提升模型在单机/集群场景下不同GPU/NPU硬件平台的运行效率 2.开发创新推理加速方案，通过投机采样算法改进、MTP机制优化等框架级特性，提升MOE架构模型推理效率；并通过优化集群并行推理场景的专家负载均衡、计算/通信 Overlap 等特性，提升集群级别的推理效率 3.完成 W8A8 等量化算法研发，并在框架层面支持量化模式下的 TP、EP 等并行模式的性能优化 4.针对多种计算架构（NVIDIA/AMD GPU、国产化 NPU 等）进行深度硬件适配，开发高性能算子库与内存管理组件，实现跨平台性能优化与资源利用率的提升
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
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.
推理引擎+
https://www.youtube.com/watch?v=_dvk75LEJ34
https://www.youtube.com/watch?v=XtT5i0ZeHHE
算法+
https://roadmap.sh/datastructures-and-algorithms
Step by step guide to learn Data Structures and Algorithms in 2025
https://www.hellointerview.com/learn/code
A visual guide to the most important patterns and approaches for the coding interview.
https://www.w3schools.com/dsa/
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.
内核+
https://www.youtube.com/watch?v=C43VxGZ_ugU
I rummage around the Linux kernel source and try to understand what makes computers do what they do.
https://www.youtube.com/watch?v=HNIg3TXfdX8&list=PLrGN1Qi7t67V-9uXzj4VSQCffntfvn42v
Learn how to develop your very own kernel from scratch in this programming series!
https://www.youtube.com/watch?v=JDfo2Lc7iLU
Denshi goes over a simple explanation of what computer kernels are and how they work, alonside what makes the Linux kernel any special.
GPT+
https://www.youtube.com/watch?v=kCc8FmEb1nY
We build a Generatively Pretrained Transformer (GPT), following the paper "Attention is All You Need" and OpenAI's GPT-2 / GPT-3.
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.
DeepSpeed+
https://www.youtube.com/watch?v=pDGI668pNg0
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.
Llama+
https://github.com/LlamaFamily/Llama-Chinese
Llama中文社区，实时汇总最新Llama学习资料，构建最好的中文Llama大模型开源生态，完全开源可商用。
https://www.llama.com/docs/overview/
This guide provides information and resources to help you set up Llama including how to access the model, hosting, how-to and integration guides.
相关职位
社招7年以上云智能集团
1.负责服务器GPU超节点软件系统方案，主导互连软件的架构设计、研发交付、应用优化（训练及推理场景下SHMEM技术，KV Cache，共享内存，互连传输软件）等， 参与模块实现，问题攻关； 2.参与下一代数据中心服务器超节点定义、如数据面软硬件协同方案； 3. 参与行业领先的互连标准定义，以及行业生态的推动及落地； 4. 参与创新研究，发表相关技术论文，申请专利。
更新于 2025-08-01
社招7年以上技术类-开发
1、负责安全GPU推理引擎、GPU性能优化相关技术平台，解决安全大模型GPU部署的资源弹性、性能瓶颈问题 2、了解行业最新GPU、NPU等最技术优化方案以及在安全落地 3、带领团队完成Modelops平台相关项目管理，以及平台架构规划设计
更新于 2025-08-04
社招2年以上审核策略
1、负责将内容安全/商业安全的复杂治理需求，转化为基于大模型的识别方案。通过PE/RAG/Workflow等技术持续实验和优化，不断提升策略的准确率与召回率。 2、能够开发用于安全场景的Agent和Workflow，实现复杂风险场景的自动化识别、推理和处置。 3、探索大模型及Multi-Agent领域前沿技术，进行技术调研、原型搭建和效果验证，并推动其在业务场景中的规模化应用。 4、作为大模型技术在安全领域的专家，强目标导向地协同算法、研发、治理、产品等团队，明确技术路径，统筹项目资源，共同实现安全目标。 5、具备产品意识，不仅满足于解决单点问题，更致力于优化产品工具、提升整体安全运营的效率和智能化水平。
更新于 2025-09-30
社招5年以上云智能行业解决方
1、深入理解客户业务需求，帮助客户选择适合其业务场景的技术路径和产品组合，利用AI技术知识、架构方法、咨询技能来影响客户技术决策 2、与客户合作进行模型训练、推理和模型应用等POC，含展示功能、调整模型、优化模型性能、测试分析、Agent搭建、模型调用等内容 3、依据客户需求和技术研判，推动产研部门持续优化产品，助力提升产品竞争力，同时沉淀最佳实践，以及脚本、模板、参考架构等可复用的技术资产 4、持续跟踪行业动态和技术趋势，并与产品团队协作，打造创新的人工智能（大模型、智算、一体机等）解决方案 5、支持市场活动，作为领域专家参与市场洞察、行业标准、市场排名报告、白皮书撰写等活动，并在行业峰会、技术沙龙等市场活动中进行技术传播和分享
更新于 2025-06-16