The role involves conducting research on large multimodal models focusing on image and video generation and editing capabilities
Job Summary
The role involves conducting research on large multimodal models focusing on image and video generation and editing capabilities.
Candidates will explore state-of-the-art video generation models and incubate new features across device, cloud, and autonomous driving scenarios.
The position requires translating cutting-edge algorithmic innovations into deployable product solutions through close collaboration with engineering teams.
Matching Summary
Match Score: 85
The role involves conducting research on large multimodal models focusing on image and video generation and editing capabilities.
Skills & Requirements
Must-have
Master's degree in Computer Science or AI
1-5 years R&D experience in generative AI
Proficiency in Python and C++ programming
Hands-on experience with PyTorch or TensorFlow
Strong background in multimodal large models
Nice-to-have
First-author publications in top-tier conferences
Experience with reinforcement learning techniques
Practical experience with visual data annotation
Collaborative team-oriented mindset
Broad technical vision in generative AI
Key Requirements
Master's degree or above in related fields
1–5 years relevant research or development experience