混元AIGC算法研究员（文生图）（深圳/北京/上海））
Tencent
混元AIGC算法研究员（文生图）（深圳/北京/上海））
Job Description
混元AIGC算法研究员（文生图）（深圳/北京/上海））
📋 Job Overview
The role focuses on researching and optimizing AI generation models for text-to-image and multimodal content at Tencent. Responsibilities include improving generation quality, diversity, controllability, and efficiency to enhance user experience and support product deployment. The position involves algorithm training in image generation, multimodal large models, and small-sample learning, addressing business challenges in AI painting, text, and video generation.
📍 Location: Shenzhen, China
🏢 Business Unit: TEG
📄 Full Description
1.通过内容（文本/图像/音频/3D模型等）生成模型的研究优化，解决目前算法在生成质量、多样性、可控性、生成效率等上的问题，并最终有效改善用户体验和生产效能，协助算法的产品化落地；
2.从事图像生成、多模态大模型、小样本学习领域算法训练和优化；
3.结合自有产品和业务需求，从 prompt优化、生成模型研发、adapter研发，性能加速等方面优化Α绘画，AI文字生成，Al视频生成等效果和体验，解决面向业务场景的应用和落地时的算法卡点问题；
4.解决多模态生成模型的工业化部署问题，深入探索模型设计和优化的研发工作。
2.从事图像生成、多模态大模型、小样本学习领域算法训练和优化；
3.结合自有产品和业务需求，从 prompt优化、生成模型研发、adapter研发，性能加速等方面优化Α绘画，AI文字生成，Al视频生成等效果和体验，解决面向业务场景的应用和落地时的算法卡点问题；
4.解决多模态生成模型的工业化部署问题，深入探索模型设计和优化的研发工作。
🎯 Key Responsibilities
- Research and optimize content generation models (text/image/audio/3D models) to address issues in generation quality, diversity, controllability, efficiency, and improve user experience and productivity for product deployment.
- Engage in algorithm training and optimization for image generation, multimodal large models, and small-sample learning.
- Optimize AI painting, text generation, and video generation based on product and business needs, including prompt optimization, model development, adapter research, and performance acceleration to solve application bottlenecks.
- Resolve industrialization deployment issues for multimodal generation models and explore model design and optimization research.
🛠️ Required Skills
- Expertise in AI generation models, particularly text-to-image and multimodal models
- Knowledge of algorithm optimization for quality, diversity, controllability, and efficiency
- Experience in image generation, multimodal large models, and small-sample learning
- Skills in prompt optimization, model development, adapter research, and performance acceleration
- Proficiency in industrial deployment of AI models
Locations
- Shenzhen, China
Salary
Estimated Salary Rangemedium confidence
400,000 - 800,000 CNY / yearly
Source: ai estimated
* This is an estimated range based on market data and may vary based on experience and qualifications.
Skills Required
- Expertise in AI generation models, particularly text-to-image and multimodal modelsintermediate
- Knowledge of algorithm optimization for quality, diversity, controllability, and efficiencyintermediate
- Experience in image generation, multimodal large models, and small-sample learningintermediate
- Skills in prompt optimization, model development, adapter research, and performance accelerationintermediate
- Proficiency in industrial deployment of AI modelsintermediate
Responsibilities
- Research and optimize content generation models (text/image/audio/3D models) to address issues in generation quality, diversity, controllability, efficiency, and improve user experience and productivity for product deployment.
- Engage in algorithm training and optimization for image generation, multimodal large models, and small-sample learning.
- Optimize AI painting, text generation, and video generation based on product and business needs, including prompt optimization, model development, adapter research, and performance acceleration to solve application bottlenecks.
- Resolve industrialization deployment issues for multimodal generation models and explore model design and optimization research.
Tags & Categories
混元AIGC算法研究员（文生图）（深圳/北京/上海））
Tencent
混元AIGC算法研究员（文生图）（深圳/北京/上海））
Job Description
混元AIGC算法研究员（文生图）（深圳/北京/上海））
📋 Job Overview
The role focuses on researching and optimizing AI generation models for text-to-image and multimodal content at Tencent. Responsibilities include improving generation quality, diversity, controllability, and efficiency to enhance user experience and support product deployment. The position involves algorithm training in image generation, multimodal large models, and small-sample learning, addressing business challenges in AI painting, text, and video generation.
📍 Location: Shenzhen, China
🏢 Business Unit: TEG
📄 Full Description
1.通过内容（文本/图像/音频/3D模型等）生成模型的研究优化，解决目前算法在生成质量、多样性、可控性、生成效率等上的问题，并最终有效改善用户体验和生产效能，协助算法的产品化落地；
2.从事图像生成、多模态大模型、小样本学习领域算法训练和优化；
3.结合自有产品和业务需求，从 prompt优化、生成模型研发、adapter研发，性能加速等方面优化Α绘画，AI文字生成，Al视频生成等效果和体验，解决面向业务场景的应用和落地时的算法卡点问题；
4.解决多模态生成模型的工业化部署问题，深入探索模型设计和优化的研发工作。
2.从事图像生成、多模态大模型、小样本学习领域算法训练和优化；
3.结合自有产品和业务需求，从 prompt优化、生成模型研发、adapter研发，性能加速等方面优化Α绘画，AI文字生成，Al视频生成等效果和体验，解决面向业务场景的应用和落地时的算法卡点问题；
4.解决多模态生成模型的工业化部署问题，深入探索模型设计和优化的研发工作。
🎯 Key Responsibilities
- Research and optimize content generation models (text/image/audio/3D models) to address issues in generation quality, diversity, controllability, efficiency, and improve user experience and productivity for product deployment.
- Engage in algorithm training and optimization for image generation, multimodal large models, and small-sample learning.
- Optimize AI painting, text generation, and video generation based on product and business needs, including prompt optimization, model development, adapter research, and performance acceleration to solve application bottlenecks.
- Resolve industrialization deployment issues for multimodal generation models and explore model design and optimization research.
🛠️ Required Skills
- Expertise in AI generation models, particularly text-to-image and multimodal models
- Knowledge of algorithm optimization for quality, diversity, controllability, and efficiency
- Experience in image generation, multimodal large models, and small-sample learning
- Skills in prompt optimization, model development, adapter research, and performance acceleration
- Proficiency in industrial deployment of AI models
Locations
- Shenzhen, China
Salary
Estimated Salary Rangemedium confidence
400,000 - 800,000 CNY / yearly
Source: ai estimated
* This is an estimated range based on market data and may vary based on experience and qualifications.
Skills Required
- Expertise in AI generation models, particularly text-to-image and multimodal modelsintermediate
- Knowledge of algorithm optimization for quality, diversity, controllability, and efficiencyintermediate
- Experience in image generation, multimodal large models, and small-sample learningintermediate
- Skills in prompt optimization, model development, adapter research, and performance accelerationintermediate
- Proficiency in industrial deployment of AI modelsintermediate
Responsibilities
- Research and optimize content generation models (text/image/audio/3D models) to address issues in generation quality, diversity, controllability, efficiency, and improve user experience and productivity for product deployment.
- Engage in algorithm training and optimization for image generation, multimodal large models, and small-sample learning.
- Optimize AI painting, text generation, and video generation based on product and business needs, including prompt optimization, model development, adapter research, and performance acceleration to solve application bottlenecks.
- Resolve industrialization deployment issues for multimodal generation models and explore model design and optimization research.
Tags & Categories