微信秒剪-大模型算法研究员-多模态方向
Tencent
微信秒剪-大模型算法研究员-多模态方向
Job Description
微信秒剪-大模型算法研究员-多模态方向
📋 Job Overview
The position is for a Large Model Algorithm Researcher in the Multimodal Direction at WeChat's Video Editing team (微信秒剪). The role focuses on developing and implementing multimodal algorithms for content understanding and generation in video editing applications. Responsibilities include model design, optimization, and exploring cutting-edge technologies like multimodal large models to enhance business applications.
📍 Location: Beijing, China
🏢 Business Unit: WXG
📄 Full Description
2.图像、视频、语音等多模态内容理解和生成算法的模型设计、训练、优化；
3.文生图、文生视频、图生视频等算法的探索和落地；
4.实现模型轻量化（知识蒸馏、量化剪枝）及推理加速，满足低延迟需求；
5.跟踪多模态大模型、世界模型等前沿方向，探索业务结合点。
🎯 Key Responsibilities
- Responsible for the implementation of multimodal content understanding, multimodal generation, and other algorithm technologies in video editing, multimodal understanding, and generation business.
- Design, training, and optimization of models for multimodal content understanding and generation in images, videos, speech, etc.
- Exploration and implementation of algorithms such as text-to-image, text-to-video, image-to-video, etc.
- Implement model lightweighting (knowledge distillation, quantization pruning) and inference acceleration to meet low-latency requirements.
- Track cutting-edge directions such as multimodal large models and world models, and explore business integration points.
Locations
- Beijing, China
Salary
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.
Responsibilities
- Responsible for the implementation of multimodal content understanding, multimodal generation, and other algorithm technologies in video editing, multimodal understanding, and generation business.
- Design, training, and optimization of models for multimodal content understanding and generation in images, videos, speech, etc.
- Exploration and implementation of algorithms such as text-to-image, text-to-video, image-to-video, etc.
- Implement model lightweighting (knowledge distillation, quantization pruning) and inference acceleration to meet low-latency requirements.
- Track cutting-edge directions such as multimodal large models and world models, and explore business integration points.
Tags & Categories
Answer 10 quick questions to check your fit for 微信秒剪-大模型算法研究员-多模态方向 @ Tencent.
Related Books and Jobs
微信秒剪-大模型算法研究员-多模态方向
Tencent
微信秒剪-大模型算法研究员-多模态方向
Job Description
微信秒剪-大模型算法研究员-多模态方向
📋 Job Overview
The position is for a Large Model Algorithm Researcher in the Multimodal Direction at WeChat's Video Editing team (微信秒剪). The role focuses on developing and implementing multimodal algorithms for content understanding and generation in video editing applications. Responsibilities include model design, optimization, and exploring cutting-edge technologies like multimodal large models to enhance business applications.
📍 Location: Beijing, China
🏢 Business Unit: WXG
📄 Full Description
2.图像、视频、语音等多模态内容理解和生成算法的模型设计、训练、优化；
3.文生图、文生视频、图生视频等算法的探索和落地；
4.实现模型轻量化（知识蒸馏、量化剪枝）及推理加速，满足低延迟需求；
5.跟踪多模态大模型、世界模型等前沿方向，探索业务结合点。
🎯 Key Responsibilities
- Responsible for the implementation of multimodal content understanding, multimodal generation, and other algorithm technologies in video editing, multimodal understanding, and generation business.
- Design, training, and optimization of models for multimodal content understanding and generation in images, videos, speech, etc.
- Exploration and implementation of algorithms such as text-to-image, text-to-video, image-to-video, etc.
- Implement model lightweighting (knowledge distillation, quantization pruning) and inference acceleration to meet low-latency requirements.
- Track cutting-edge directions such as multimodal large models and world models, and explore business integration points.
Locations
- Beijing, China
Salary
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.
Responsibilities
- Responsible for the implementation of multimodal content understanding, multimodal generation, and other algorithm technologies in video editing, multimodal understanding, and generation business.
- Design, training, and optimization of models for multimodal content understanding and generation in images, videos, speech, etc.
- Exploration and implementation of algorithms such as text-to-image, text-to-video, image-to-video, etc.
- Implement model lightweighting (knowledge distillation, quantization pruning) and inference acceleration to meet low-latency requirements.
- Track cutting-edge directions such as multimodal large models and world models, and explore business integration points.
Tags & Categories
Answer 10 quick questions to check your fit for 微信秒剪-大模型算法研究员-多模态方向 @ Tencent.
Related Books and Jobs