拼多多大模型推理系统工程师
社招全职技术类地点：上海状态：招聘
任职要求
任职要求 1）扎实的编程能力（Python / C++ / Rust 至少一种）； 2）良好的数据结构与算法基础； 3）理解操作系统、并发编程、网络基础； 4）具备性能分析能力（CPU / GPU / IO / 调度）； 5）理解高并发系统设计（缓存、队列、负载均衡）； 6）理解 Transformer 与大模型基本推理流程； 7）理解 KV Cache、batching、token streaming 等…
登录查看完整任职要求
微信扫码，1秒登录
工作职责
岗位职责 1）推理调度系统：设计 batching / admission control / 请求调度策略，提升吞吐与稳定性； 2）KV Cache 系统：设计 cache 生命周期管理、复用策略与显存优化机制； 3）Decoding 优化：实现 speculative decoding / prefix reuse / 并行解码策略； 4）推理执行引擎：参与执行图、算子调度、runtime 优化； 5）GPU 利用率优化：分析 kernel、IO、调度瓶颈，提升整体利用率； 6）分布式推理：构建高并发在线服务，支持大规模请求负载； 7）训练协同：支持 RL rollout / evaluation 场景中的推理加速。
包括英文材料
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.
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
Rust+
https://www.youtube.com/watch?v=BpPEoZW5IiY
In this comprehensive Rust course for beginners, you will learn about the core concepts of the language and underlying mechanisms in theory.
https://www.youtube.com/watch?v=lzKeecy4OmQ
Full Rust 101 Crash Course for beginners.
https://www.youtube.com/watch?v=rQ_J9WH6CGk
数据结构+
https://www.youtube.com/watch?v=8hly31xKli0
In this course you will learn about algorithms and data structures, two of the fundamental topics in computer science.
https://www.youtube.com/watch?v=B31LgI4Y4DQ
Learn about data structures in this comprehensive course. We will be implementing these data structures in C or C++.
https://www.youtube.com/watch?v=CBYHwZcbD-s
Data Structures and Algorithms full course tutorial java
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/
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
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.
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
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.
还有更多 •••
相关职位
社招程序&技术类
1、负责公司各AI推理场景（LLM/多模态/视频等）的推理系统研发和性能优化、资源调度、可观测性搭建、日常维护等工作 2、与算法团队深度合作，进行算法与系统的联合设计与优化（如模型量化、kvcache量化、投机采样等） 3、保持关注行业前沿技术，且有能力和热情开展创新研究
北京
社招信息技术类
【】 1、负责大模型训练和推理系统的研发与性能优化，包括但不限于：模型计算性能优化、训练集群调优、分布式大模型推理系统、大规模推理流量调度等； 2、负责解决系统高并发、高可靠性、高可扩展性等技术难关； 3、负责大模型训练和推理前瞻性技术架构的调研和引入，技术方案不限于子图匹配、编译优化、模型量化等； 4、负责异构硬件的引入与训练推理框架的集成，包括但不限于GPU、NPU、TPU等； 5、算法部门深度合作，进行算法与系统的联合优化。
更新于 2025-12-18深圳
社招A157899
1、负责火山引擎大模型训练和推理系统的研发与性能优化，包括但不限于：模型计算性能优化、千卡训练集群调优、分布式大模型推理系统、大规模推理流量调度等； 2、负责解决系统高并发、高可靠性、高可扩展性等技术难关，支撑火山引擎千亿级别的日均Token训练推理流量； 3、负责大模型训练和推理前瞻性技术架构的调研和引入，技术方案不限于子图匹配、编译优化、模型量化等； 4、负责异构硬件的引入与训练推理框架的集成，包括但不限于GPU、NPU、TPU 等； 5、面向全球多地域超大规模GPU算力集群，通过弹性调度、GPU超卖、任务编排等方式不断提升算力利用率； 6、与算法部门深度合作，进行算法与系统的联合优化。
更新于 2024-08-26北京
社招A136215
1、负责火山引擎大模型训练和推理系统的研发与性能优化，包括但不限于：模型计算性能优化、千卡训练集群调优、分布式大模型推理系统、大规模推理流量调度等； 2、负责解决系统高并发、高可靠性、高可扩展性等技术难关，支撑火山引擎千亿级别的日均Token训练推理流量； 3、负责大模型训练和推理前瞻性技术架构的调研和引入，技术方案不限于子图匹配、编译优化、模型量化等； 4、负责异构硬件的引入与训练推理框架的集成，包括但不限于GPU、NPU、TPU等； 5、面向全球多地域超大规模GPU算力集群，通过弹性调度、GPU超卖、任务编排等方式不断提升算力利用率； 6、与算法部门深度合作，进行算法与系统的联合优化。
更新于 2024-08-28杭州