
美图高级计算机视觉工程师(视频混剪)/ Senior Computer Vision Engineer (Video Intelligent Editing)
社招全职算法类地点:北京状态:招聘
任职要求
1. Bachelor’s degree or above in Computer Science or a related field, with at least 5 years of work experience and proven experience in full-cycle algorithm project development and deployment. 2. Proficient in the principles of deep neural network models such as Transformer, DiT, Diffusion, and CNN, with hands-on project experience. Deep understanding of machine learning, image and video processing algorithms. 3. Strong proficiency in PyTorch or TensorFlow deep learning frameworks, excellent algorithm implementation skills, familiarity with algorithm performance tuning techniques, and the abil…
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: 深度融入公司 AIGC 项目团队,聚焦于多模态内容理解、视频智能混剪等前沿算法的研发与持续优化工作,通过创新技术为产品赋能,推动项目高效落地。 任职资格: 1.本科及以上学历,计算机相关专业,5年以上工作经验,具备完整算法项目研发及落地经验者 2. 掌握Transformer、Dit、Diffusion、CNN等深度神经网络模型原理,并有实际项目应用经验,对机器学习、图像与视频处理算法有深入理解; 3.熟练掌握pytorch或tensorflow深度学习框架,优秀的算法实现能力,熟悉算法性能调优技巧,能独立承担复杂算法模块的开发与优化工作; 4.有视频内容理解、视频生成、文生图、多模态模型等相关项目研发经验者优先; 5.较强的分析问题和解决问题的能力,能熟练阅读并理解领域内英文技术文章或论文; 6.良好的沟通协作精神,能与团队成员、跨部门同事高效配合,共同攻克技术难题; 7. 在计算机视觉领域顶级会议发表论文者优先考虑。 Job Title: Senior Computer Vision Engineer (Video Intelligent Editing) Responsibilities: Deeply integrate into the company’s AIGC project team, focusing on the R&D and continuous optimization of cutting-edge algorithms such as multimodal content understanding and intelligent video editing. Leverage innovative technologies to empower products and drive efficient project delivery.
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/
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.
CNN+
https://learnopencv.com/understanding-convolutional-neural-networks-cnn/
Convolutional Neural Network (CNN) forms the basis of computer vision and image processing.
[英文] CNN Explainer
https://poloclub.github.io/cnn-explainer/
Learn Convolutional Neural Network (CNN) in your browser!
https://www.deeplearningbook.org/contents/convnets.html
Convolutional networks(LeCun, 1989), also known as convolutional neuralnetworks, or CNNs, are a specialized kind of neural network for processing data.
https://www.youtube.com/watch?v=2xqkSUhmmXU
MIT Introduction to Deep Learning 6.S191: Lecture 3 Convolutional Neural Networks for Computer Vision
还有更多 •••
相关职位
社招3-5年网易伏羲
1、 负责人体动作动画相关业务(包括但不限于动作迁移、动作生成、动作理解、运动控制)的算法研究、技术选型、系统架构设计与工程实现 2、 主导基于PyTorch/TensorFlow等深度学习框架的高性能、可复现的代码开发与模型训练,构建业界领先的动作AI系统 3、 持续优化动作算法在工程落地中的效果、性能与鲁棒性,设计和开发高并发、低延迟的动作数据处理与服务平台,保障线上服务的稳定性与可扩展性 4、 深入跟踪并探索计算机视觉、图形学与多模态大模型领域的前沿技术进展,并能将其转化为实际的技术创新与业务应用
更新于 2026-07-13杭州
社招算法
负责感知算法相关研究、开发与产品化,包括但不限于: 1. 负责承接多模态感知算法,包括但不限于视觉、激光雷达、毫米波雷达的深度、检测、分割、occ、动态等感知任务,并落地产品 2. 结合自研平台硬件设计,选择高效的backbone和网络结构,并对网络进行压缩部署,实现高效端侧部署 3. 负责研究视觉相机、结构光、激光雷达等传感器的特性,开发相关的传感器算法并落地产品 4. 跟进调研最新的网络算法,并且导入新网络改善感知能力。
更新于 2026-07-02深圳
社招算法
负责端到端感知算法相关研究、开发与产品化,包括但不限于: 1. 负责承接端到端感知算法,包括但不限于视觉、激光雷达、毫米波雷达的深度、检测、分割、occ、动态等感知任务,并落地产品 2. 结合自研平台硬件设计,选择高效的backbone和网络结构,并对网络进行压缩部署,实现高效端侧部署 3. 负责研究视觉相机、结构光、激光雷达等传感器的特性,开发相关的传感器算法并落地产品 4. 跟进调研最新的网络算法,并且导入新网络改善感知能力。
更新于 2026-05-31深圳|上海|北京