快手算法工程师(端智能方向)-【主站】
社招全职3-5年J0011地点:北京状态:招聘
任职要求
1、有短视频观看/消费体验优化相关工作经验者优先,有推荐算法/广告营销算法/用户增长等toC经验者优先; 2、有端智能、物联网、端云协同、联邦学习、因果推断、SLM等细分领域实践经验者优先; 3、优秀的算法和编程能力,精通Python,熟悉大数据处理工具Hive、Hadoop等,熟悉主流深度学习工具…
登录查看完整任职要求
微信扫码,1秒登录
工作职责
1、负责快手APP视频流端上重排支撑,负责训练收数逻辑开发、实时特征挖掘、模型部署等工作; 2、对短视频观看/消费体验优化领域的算法做功点发掘、设计部署、实验验证等,包括不限于以下几个方向: 2.1 通过模型实时预估引导用户至其它页面或功能的价值,以提升引导ctr、cvr等,降低打扰感、提升用户体验; 2.2 通过模型预估完成姿态、左右手、继续观看时长等高级特征挖掘,用于更多体验优化场景; 3、负责已有模型性能优化、量化压缩等,参与端云协同的系统架构设计等; 4、参与SLM在客户端上的部署及应用探索。
包括英文材料
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/
因果推断+
https://web.stanford.edu/~swager/causal_inf_book.pdf
How best to understand and characterize causality is an age-old question in philosophy.
客户端开发+
https://developer.mozilla.org/zh-CN/docs/Learn_web_development/Core/Frameworks_libraries/Introduction
简要回顾 JavaScript 和框架的历史,为什么框架会存在以及它们提供了什么,如何开始考虑选择一个框架并学习,以及对于客户端框架还有什么替代方案。
https://gamefromscratch.com/the-best-game-development-frameworks/
If you are looking to create a game but perhaps want to craft your own game engine from existing technologies, or you prefer to work at a lower more code focused level, using a game framework instead of a game engine may be right for you.
机器学习+
https://www.youtube.com/watch?v=0oyDqO8PjIg
Learn about machine learning and AI with this comprehensive 11-hour course from @LunarTech_ai.
https://www.youtube.com/watch?v=i_LwzRVP7bg
Learn Machine Learning in a way that is accessible to absolute beginners.
https://www.youtube.com/watch?v=NWONeJKn6kc
Learn the theory and practical application of machine learning concepts in this comprehensive course for beginners.
https://www.youtube.com/watch?v=PcbuKRNtCUc
Learn about all the most important concepts and terms related to machine learning and AI.
深度学习+
https://d2l.ai/
Interactive deep learning book with code, math, and discussions.
NLP+
https://www.youtube.com/watch?v=fNxaJsNG3-s&list=PLQY2H8rRoyvzDbLUZkbudP-MFQZwNmU4S
Welcome to Zero to Hero for Natural Language Processing using TensorFlow!
https://www.youtube.com/watch?v=R-AG4-qZs1A&list=PLeo1K3hjS3uuvuAXhYjV2lMEShq2UYSwX
Natural Language Processing tutorial for beginners series in Python.
https://www.youtube.com/watch?v=rmVRLeJRkl4&list=PLoROMvodv4rMFqRtEuo6SGjY4XbRIVRd4
The foundations of the effective modern methods for deep learning applied to NLP.
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.
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.
Kotlin+
https://kotlinlang.org/docs/kotlin-tour-welcome.html
Quickly learn the essentials of the Kotlin programming language through our tours, which will take you from beginner to intermediate level.
https://learnxinyminutes.com/kotlin/
Kotlin is a statically typed programming language for the JVM, Android and the browser. It is 100% interoperable with Java.
https://www.youtube.com/watch?v=EExSSotojVI
In this full Kotlin course, you will learn the most popular programming language on Android and start building your own apps.
Hive+
[英文] Hive Tutorial
https://www.tutorialspoint.com/hive/index.htm
Hive is a data warehouse infrastructure tool to process structured data in Hadoop. It resides on top of Hadoop to summarize Big Data, and makes querying and analyzing easy.
https://www.youtube.com/watch?v=D4HqQ8-Ja9Y
Hadoop+
https://www.runoob.com/w3cnote/hadoop-tutorial.html
Hadoop 为庞大的计算机集群提供可靠的、可伸缩的应用层计算和存储支持,它允许使用简单的编程模型跨计算机群集分布式处理大型数据集,并且支持在单台计算机到几千台计算机之间进行扩展。
[英文] Hadoop Tutorial
https://www.tutorialspoint.com/hadoop/index.htm
Hadoop is an open-source framework that allows to store and process big data in a distributed environment across clusters of computers using simple programming models.
Spark+
[英文] Learning Spark Book
https://pages.databricks.com/rs/094-YMS-629/images/LearningSpark2.0.pdf
This new edition has been updated to reflect Apache Spark’s evolution through Spark 2.x and Spark 3.0, including its expanded ecosystem of built-in and external data sources, machine learning, and streaming technologies with which Spark is tightly integrated.
还有更多 •••
相关职位
社招5-10年J0011
1、负责精准投放相关算法的设计、技术规划、产品落地、迭代优化等; 2、负责短视频消费场景中的算法相关需求发掘、设计、技术研发,以及推动上线落地和不断迭代优化; 3、跟踪前沿的算法理论,并且将优秀的算法应用到业务场景中,提升业务效果; 4、推进基于AB的科学实验; 5、进行大模型reasoning能力的相关研究,借助SFT / DPO / self-play等手段,提高模型在代码数学等推理任务上的表现。
更新于 2025-07-22北京
社招1-3年J0012
1、负责快手APP视频流端上重排支撑,负责训练收数逻辑开发、实时特征挖掘、模型部署等工作; 2、对短视频观看/消费体验优化领域的算法做功点发掘、设计部署、实验验证等,包括不限于以下几个方向; 2.1 通过模型实时预估引导用户至其它页面或功能的价值,以提升引导ctr、cvr等,降低打扰感、提升用户体验; 2.2 通过模型预估完成姿态、左右手、继续观看时长等高级特征挖掘,用于更多体验优化场景; 3、负责已有模型性能优化、量化压缩等,参与端云协同的系统架构设计等; 4、参与SLM、VLM在客户端上的部署及应用探索。
更新于 2026-03-12北京
社招1-3年J0012
你将与一群“可能是行业内最顶尖的”Java后端工程师一起,共同搭建业界领先的直播平台。在这里你将: 1、参与快手直播营收系统的研发工作,深入发掘和分析业务需求,撰写技术方案和系统设计,通过敏捷开发支持产品需求快速迭代,支撑业务规模增长; 2、接受高并发、海量资金以及数据的挑战,分析和发现系统的优化点,负责推动系统易用、扩展、可用性、资金安全性、性能等提升; 3、参与直播营收业务与AI技术的深度融合,并结合业务具体场景给出工业化落地方案,提高直播流水; 4、探索AI领域最新的技术和趋势,为团队引入创新的技术、创新的解决方案,用创新的思路解决问题。
更新于 2026-03-12北京