传音资深CV算法专家(人像编辑方向)(J15971)
社招全职地点:上海 | 深圳状态:招聘
任职要求
1. 计算机、人工智能或相关专业硕士及以上学历,具备扎实的数学与深度学习基础。
2. 熟悉扩散模型、视觉生成大模型、人像方向相关技术。
3. 具备模型部署经验者优先(TensorRT、ONNX、端侧加速)。
4. 对 AIGC 影像方向有热情,愿意在手…登录查看完整任职要求
微信扫码,1秒登录
工作职责
1. 负责手机端与云端 AIGC 影像技术研发,包括高质量的人像生成、图像修复、人像编辑等核心算法设计与优化。 2. 负责扩散模型、单步生成模型、图像编辑模型的研发、微调、蒸馏与加速。 3. 针对海外新兴市场的拍摄习惯和弱光、逆光、中低端机等复杂环境,设计稳健的人像处理与编辑方案。 4. 参与构建手机影像 AIGC 能力体系,包括数据 pipeline、模型评价体系与端云协同架构优化。 5. 跟踪行业技术前沿(Diffusion, Flow-based, MMDiT, Rectified Flow等),并在产品侧落地创新。
包括英文材料
OpenCV+
https://learnopencv.com/getting-started-with-opencv/
At LearnOpenCV we are on a mission to educate the global workforce in computer vision and AI.
https://opencv.org/university/free-opencv-course/
This free OpenCV course will teach you how to manipulate images and videos, and detect objects and faces, among other exciting topics in just about 3 hours.
图像处理+
https://opencv.org/blog/computer-vision-and-image-processing/
This fascinating journey involves two key fields: Computer Vision and Image Processing.
https://www.geeksforgeeks.org/python/image-processing-in-python/
Image processing involves analyzing and modifying digital images using computer algorithms.
https://www.youtube.com/watch?v=kSqxn6zGE0c
In this Introduction to Image Processing with Python, kaggle grandmaster Rob Mulla shows how to work with image data in python!
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/
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.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.
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
Stable Diffusion+
https://course.fast.ai/Lessons/lesson9.html
This lesson starts with a tutorial on how to use pipelines in the Diffusers library to generate images.
https://www.youtube.com/watch?v=dMkiOex_cKU
earn how to use Stable Diffusion to create art and images in this full course.
CVPR+
https://cvpr.thecvf.com/
还有更多 •••
相关职位
社招
1. 负责 AIGC基础模型(文生图、图生图、图像编辑模型)的后训练体系建设,包括SFT、DPO、GRPO等强化学习方法设计与实现。 2. 构建大规模指令数据,用于人像生成、人像编辑、图像修复、目标消除、视频编辑等方向的SFT微调。 3. 设计奖励模型(Reward Model),包括但不限于:图像质量、真实感、结构保持;人像一致性、身份保持指令遵循与安全性。 4. 负责从通用基础模型到手机影像场景的能力迁移,指令适配、风格对齐等。 5. 提升模型对用户指令的理解能力,使生成编辑结果更稳定、更可控、更一致。
更新于 2024-12-06上海|深圳
社招1年以上信息技术类
岗位描述 1. 负责多模态大模型(包括但不限于视觉、语言等领域)的后训练算法设计与实现,主要涉及SFT(Supervised Fine-Tuning)、RL(Reinforcement Learning)等优化技术。 2. 在模型训练后期进行性能优化和算法调优,提升模型的泛化能力、精度和效能。 3. 参与多模态大模型的蒸馏、压缩等加速算法的研究与落地工作。 4. 支持与跨团队合作,推动多模态大模型在业务场景中的应用与迭代。
更新于 2026-07-01深圳
社招网易游戏(互娱)
1.负责自研引擎的shader、pso、材质变体、shader cache等流程管理优化; 2.负责各平台RHI层接入适配优化; 3.负责游戏客户端引擎渲染相关功能模块设计与移动端落地; 4.与美术直接合作,满足其他职能引擎相关需求并共同推进画面表现提升; 5.负责游戏客户端性能优化以及稳定性提高;
更新于 2026-06-15杭州