
美图计算机视觉数据工程师(实习生)
实习兼职美图影像研究院地点:深圳状态:招聘
任职要求
● 计算机/电子信息/数学或相关专业的硕士生 ● 熟练掌握 Python 编程,了解常见深度学习框架(尤其是PyTorch) ● 有实算机视觉或生成模型相关经验(项目 / 实习均可) ● 有一定理解英文文献论文以及沟通的能力 ● 能够独立相关文献,跑通开源 GenAI 模型,具备调试和实验能力 ● 有责任心和所有权意识,积极主动 ● 具备良好的问题解决能力,沟通能力和实验记录习惯 ● 一周可实习5至少可以实习3个月 加分项: ● 掌握C/C++,有AI辅助编程工具使用经验 ● 有计算机图形仿真或3D 引擎使用经验(即使是课程或个人项目) ● 熟悉视频处理工作 ● 了解数据集构建流程,例如数据标注、组织、质量控制等等 ● 有视频特效、生成式媒体相关创作经验 Title: Computer Vision Engineer Intern Location: Shenzhen Main Job Directions: ● Computer vision and machine learning. ● Multimodal image and video generation. ● Data analysis, quality monitoring, and data processing. Key Responsibilities: ● Construct and execute inference workflows for generative models to facilitate the generation of diverse video data. ● Participate in the design and rendering of synthetic video scenarios to enhance data diversity and coverage. ● Develop automated scripts and tools to support data generation, processing, and structured management. ● Assist in building high-quality video datasets to provide support for subsequent model training and evaluation. ● Collaborate with team members to resolve model and data-related issues, and conduct experimental analysis and comparisons. Qualifications: ● Master's student in Computer Science, Electronic Information, Mathematics or related fields, or exceptionally outstanding undergraduate student. ● Proficiency in Python programming and knowledge of common deep learning frameworks (especially PyTorch). ● Practical experience in computer vision or generative models (either from projects or internships). ● Certain ability to understand English literature and papers, as well as communication skills. ● Capable of independently reading relevant literature, running open-source GenAI models, and possessing debugging and experimental capabilities. ● Strong sense of responsibility and ownership, proactive work attitude. ● Excellent problem-solving skills, communication abilities, and habits of experimental documentation. ● Availability to intern 5 days a week for at least 3 months. Preferred Qualifications: ● Proficiency in C/C++ and experience with AI-assisted programming tools. ● Experience with computer graphics simulation or 3D engine usage (even from coursework or personal projects). ● Familiarity with video processing tasks. ● Knowledge of dataset construction processes, such as data annotation, organization, and quality control. ● Experience in video effects and generative media creation.
工作职责
美图影像研究院(MT Lab)专注于计算机视觉、深度学习与计算机图形学等前沿算法的研究与应用。我们为美图产品提供核心技术支持。团队汇聚顶尖人才,致力于推动影像技术的突破,让科技与艺术美好交汇。 MT Lab focuses on R&D of cutting-edge algorithms in CV, deepearning, and computer graphics. We provide core technicalsupport for Meitu products.Our team of top talent is dedicated to advancing imagingtechnology, beautifully merging science and art. 岗位名称:计算机视觉实习生 工作地点:深圳 主要岗位方向: ● 计算机视觉和机器学习 ● 多模态的图片及视频生成 ● 数据分析,质量监控和数据处理 岗位职责: ● 搭建并运行生成式模型的推理流程,用于多样化视频数据的生成 ● 参与设计和渲染合成视频场景,提升数据的多样性与覆盖度 ● 开发自动化脚本和工具,支持数据生成、处理和结构化管理 ● 协助构建高质量视频数据集,为后续的模型训练与评估提供支持 ● 团队成员协作,解决模型与数据相关的问题,并进行实验性分析与对比
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.
深度学习+
https://d2l.ai/
Interactive deep learning book with code, math, and discussions.
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.
C+
https://www.freecodecamp.org/chinese/news/the-c-beginners-handbook/
本手册遵循二八定律。你将在 20% 的时间内学习 80% 的 C 编程语言。
https://www.youtube.com/watch?v=87SH2Cn0s9A
https://www.youtube.com/watch?v=KJgsSFOSQv0
This course will give you a full introduction into all of the core concepts in the C programming language.
https://www.youtube.com/watch?v=PaPN51Mm5qQ
In this complete C programming course, Dr. Charles Severance (aka Dr. Chuck) will help you understand computer architecture and low-level programming with the help of the classic C Programming language book written by Brian Kernighan and Dennis Ritchie.
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
相关职位
实习淘天集团日常实习
1. 多模态大模型(包括但不限于大模型预训练、垂域微调SFT、RLHF、数据治理飞轮、训练部署加速等); 2. 图像/多模态理解(包括商品多模态理解VG、目标检测、OCR、图像/多模态表征等); 3. 其他任何感兴趣/有价值的方向也欢迎交流讨论。 【实习工作环境】 1. 充裕的GPU资源; 2. 海量业务数据和基础能力积累,帮助高效产出; 3. 来自国内外top学校的师兄/师姐的倾力指导; 4. 充分尊重实习生个人意见,自由度高; 5. 产研结合,支持鼓励实习生投递顶会论文。
更新于 2025-05-06
实习
1、深入调研多模态、计算机视觉和自然语言处理等方向的前沿技术 2、推进视觉信息语义分割与编码的研究,设计自监督学习任务,在大数据上训练较大参数规模模型; 3、探索视觉与语言的语义对齐方法,和多模态多任务联合训练
更新于 2025-03-18
实习
1、调研多模态大模型等领域的前沿算法,并进行评测,给出研究报告和知识体系建设; 2、辅助完成数据采集/数据(自动)标注/模型训练评测等相关工作和流程搭建; 3、完成多模态大模型相关领域的论文,并在计算机视觉类的会议投递发表。
更新于 2025-05-06