阿里云阿里云智能-大模型推理优化专家/高级专家-杭州/北京
社招全职3年以上云智能集团地点：北京 | 杭州状态：招聘
任职要求
1. 必备技能 （1）扎实的 C++/Python 编程功底，具备模块化设计能力。 （2）大模型推理框架（vLLM/SGLang等）经验，理解模型推理原理。 （3）分布式系统开发经验，熟悉缓存、微服务与容器化技术。 （4）Linux、CUDA系统编程与性能调优能力。 2. 优先条件 （1）有推理引擎或分布式核心系统的研发经验。 （2）熟悉大模型推理优化、KVCache 机制、高性能计算。 （3）有云原生平台经验或开源社区贡献。 （4）有高并发在线服务的设计与运维经验。
工作职责
1. 核心系统研发 （1）设计与优化大模型推理服务框架与分布式缓存系统。 （2）支持多推理引擎适配、多模态推理、分布式部署及高效数据管理。 （3）开发工具链与服务化能力，包括模型量化、转换、调度与生命周期管理。 2. 性能与稳定性优化 （1）优化推理服务框架的性能，包括引擎适配、生命周期管理和资源调度。 （2）深入优化kvcache的显存、内存和存储管理、批处理、缓存策略和网络传输。 （3）支持高性能通信协议、容错与负载均衡机制。 （4）提升系统可观测性，完善监控、告警与故障恢复体系。 3. 引擎与应用集成 （1）深度集成推理引擎、缓存系统和存储系统，优化访问模式与架构设计。 （2）满足大规模、多模态推理场景下的高吞吐与低延迟需求。
包括英文材料
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
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.
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
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.
SGLang+
[英文] Install SGLang
https://docs.sglang.ai/get_started/install.html
SGLang is a fast serving framework for large language models and vision language models.
https://github.com/sgl-project/sgl-learning-materials
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
微服务+
https://learn.microsoft.com/en-us/training/modules/dotnet-microservices/
Microservice applications are composed of small, independently versioned, and scalable customer-focused services that communicate with each other by using standard protocols and well-defined interfaces.
https://microservices.io/
Microservices - also known as the microservice architecture - is an architectural style that structures an application as a collection of two or more services.
https://spring.io/microservices
Building small, self-contained, ready to run applications can bring great flexibility and added resilience to your code.
https://www.ibm.com/think/topics/microservices
Microservices, or microservices architecture, is a cloud-native architectural approach in which a single application is composed of many loosely coupled and independently deployable smaller components or services.
https://www.youtube.com/watch?v=CqCDOosvZIk
https://www.youtube.com/watch?v=hmkF77F9TLw
Learn about software system design and microservices.
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
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.
推理引擎+
https://www.youtube.com/watch?v=_dvk75LEJ34
https://www.youtube.com/watch?v=XtT5i0ZeHHE
高并发+
https://www.baeldung.com/concurrency-principles-patterns
In this tutorial, we’ll discuss some of the design principles and patterns that have been established over time to build highly concurrent applications.
https://www.baeldung.com/java-concurrency
Handling concurrency in an application can be a tricky process with many potential pitfalls. A solid grasp of the fundamentals will go a long way to help minimize these issues.
https://www.oreilly.com/library/view/concurrency-in-go/9781491941294/
You’ll understand how Go chooses to model concurrency, what issues arise from this model, and how you can compose primitives within this model to solve problems.
https://www.oreilly.com/library/view/modern-concurrency-in/9781098165406/
With this book, you'll explore the transformative world of Java 21's key feature: virtual threads.
https://www.youtube.com/watch?v=qyM8Pi1KiiM
https://www.youtube.com/watch?v=wEsPL50Uiyo
相关职位
社招3年以上技术类-开发
1、主导大模型在线推理系统的性能攻坚，构建多节点多GPU的分布式推理架构，实现智能请求调度算法与异构硬件的极致性能调优； 2、研究低bit量化、稀疏化attention等解码加速技术，在保障精度前提下显著降低计算资源消耗； 3、设计高并发场景下的负载均衡方案，构建支持动态扩展的弹性计算架构，优化推理引擎运行时环境，实现毫秒级延迟与高QPS吞吐能力。
更新于 2025-09-30
社招技术类-算法
1. 负责大模型（含多模态）及下游任务的训练及优化突破，包括但不限于：异构GPU混合训练和推理加速算法；对齐、强化学习、混合专家等大模型核心训练技术。 2. 分析和解决大模型在领域应用中的技术难题并进行突破，并与业界先进技术进行持续对比。 3. 持续关注业界最新研究动向和技术趋势，对技术方向研判选型，并进行落地。 4. 与产品和工程团队紧密合作，将先进的算法技术应用于实际产品开发。
更新于 2025-05-22
社招5年以上云智能集团
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
更新于 2025-08-14
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