安克创新AIGC算法工程师
社招全职地点:长沙 | 深圳状态:招聘
任职要求
计算机视觉、人工智能、多模态生成或相关专业硕士及以上学历,具备视频、图像、三维方向的研究或实战经验;有电商、广告、品牌内容等业务背景者优先; 精通扩散模型(Diffusion)、Transformers(ViT、TimeSformer)、Temporal U-Net、Conditioned Video Generation 等框架;熟悉Motion Module、Video Composer、Latent Consistency Models、Flow-guided Generation、ControlNet等新一代技术模块; 具备以下至少两个方向的经验优先: 文本转视频(Text-to-Video)生成与控制 图像序列生成与视频补全(inpainting, extrapolation) 视频风格迁移/风格保持(Style Transfer / Identity Preservation) 多模态驱动编辑(音频/动作/语义控制) 长视频建模与镜头结构生成 熟悉主流AI视频工具链,如Diffusers、ComfyUI插件体系,掌握FFmpeg、OpenCV、PyTorch等开源工具与部署环境;具备工程化建模与高性能推理经验(如CUDA优化、TensorRT加速、多线程分布式部署); 熟悉视频内容生产流程,了解不同业务场景(如短视频种草、品牌TVC、电商展示、KOC内容)的创意逻辑与交付需求,具备跨团队协作能力与业务理解力; 强烈的自驱力、好奇心和技术热情,愿意持续探索视频生成的边界,追求工程与算法的高融合与高价值交付。
工作职责
面向AIGC领域,研发前沿的视频生成与处理算法,结合短视频、电商、品牌创意等具体业务场景,进行系统性算法设计,推动自动化剪辑、视频生成、动作迁移、语义驱动等能力落地; 针对当前大模型视频生成中的痛点(如帧一致性、时空建模、长视频连贯性、跨模态对齐等),优化扩散/生成架构、设计稀疏高效推理策略,提高生成质量和响应速度; 开发用于视频创作的底层算法与工具链,包括视频分镜生成、关键帧补全、文本驱动编辑(text-driven editing)、镜头分割与结构化剪辑等能力模块; 持续追踪业界前沿(如Sora、Runway、Kling、Veo等),快速完成benchmark与迁移落地; 深度理解视频内容生产到多渠道分发的完整链路,与产品、运营、创意团队协同,构建适配业务的AI视频引擎与应用原型。
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.
学历+
Framer Motion+
https://motion.dev/docs/quick-start
Motion is an animation library that's easy to start and fun to master.
https://www.youtube.com/watch?v=znbCa4Rr054
Framer Motion is not only the simplest way to get up and running with animations in React JS, but also one of the most powerful.
Composer+
[英文] Introduction
https://getcomposer.org/doc/00-intro.md
Composer is a tool for dependency management in PHP.
https://learnxinyminutes.com/php-composer/
It allows you to declare the libraries your project depends on and it will manage (install/update) them for you.
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.
CUDA+
https://developer.nvidia.com/blog/even-easier-introduction-cuda/
This post is a super simple introduction to CUDA, the popular parallel computing platform and programming model from NVIDIA.
https://www.youtube.com/watch?v=86FAWCzIe_4
Lean how to program with Nvidia CUDA and leverage GPUs for high-performance computing and deep learning.
TensorRT+
https://docs.nvidia.com/deeplearning/tensorrt/latest/getting-started/quick-start-guide.html
This TensorRT Quick Start Guide is a starting point for developers who want to try out the TensorRT SDK; specifically, it demonstrates how to quickly construct an application to run inference on a TensorRT engine.
多线程+
https://liaoxuefeng.com/books/java/threading/basic/index.html
和单线程相比,多线程编程的特点在于:多线程经常需要读写共享数据,并且需要同步。
https://www.youtube.com/watch?v=_uQgGS_VIXM&list=PLsc-VaxfZl4do3Etp_xQ0aQBoC-x5BIgJ
https://www.youtube.com/watch?v=IEEhzQoKtQU
https://www.youtube.com/watch?v=mTGdtC9f4EU&list=PLL8woMHwr36EDxjUoCzboZjedsnhLP1j4
https://www.youtube.com/watch?v=TPVH_coGAQs&list=PLk6CEY9XxSIAeK-EAh3hB4fgNvYkYmghp
https://www.youtube.com/watch?v=xPqnoB2hjjA
This video is an introduction to multithreading in modern C++.
https://www.youtube.com/watch?v=YKBwKy5PrpQ
Rust threading is easy to implement and improves the efficiency of your applications on multi-core systems!
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/
相关职位

社招
1. 主导多模态生成算法(图像 / 视频 / 3D 等)的设计与优化,聚焦生成质量提升、多样性拓展、可控性强化及可编辑功能实现,攻克技术瓶颈; 2. 深度结合游戏研发与发行业务需求,提供通用性技术框架或定制化算法方案,解决 AIGC 在实际落地中的适配性、效率及效果问题,推动技术转化; 3. 密切追踪多模态与 Generative AI 领域前沿动态(如模型架构、训练策略等),结合业务痛点设计创新性算法路径,保持技术竞争力。
社招技术类
1、探索AIGC技术的相关技术,包括图片生成、视频生成、语音合成、数字人、智能对话等领域; 2、结合业务场景,设计并实现AIGC相关的算法和模型; 3、参与AIGC技术的性能优化和工程化工作; 4、持续学习和跟踪AIGC技术的最新进展,为团队提供技术支持和指导。
更新于 2025-10-08
社招MEG
-负责电商搜索场景的LLM相关算法研发工作,包括但不限于基座训练、sft、偏好对齐等 -利用LLM算法提升业务效果,包括但不限于需求理解、智能问答、优质内容生成、召回排序模块优化等 -跟进NLP/LLM/推荐/搜索等领域前沿技术 -结合产品需求推动前沿技术落地
更新于 2025-02-19