腾讯视频-影视AIGC高级算法研究员（视频生成/编辑方向）-(深圳)(杭州)
Core
Research and develop core algorithms for video generation and editing in film and television tasks, including Text-to-Video, Image-to-Video, and Video Editing.
Role type
Senior IC research scientist (video generation/editing)
Builds
Production-ready video generation and editing models for film and television post-production and short drama creation.
Domain
Film and television industry + Generative AI
Deliverable
production ML models
Required skills
Python, PyTorch, Deep Learning fundamentals, Diffusion models, Reinforcement Learning, Video Large Model pre-training/fine-tuning, RLHF, LoRA, Training parallelization frameworks
Preferred skills
Publications in CVPR, ICCV, ECCV, NeurIPS, ICLR, SIGGRAPH
Technologies
HunyuanVideo, Wan2.2/2.5, SkyReels V2, VACE, Wan-animate, ComfyUI
Responsibilities
Research and develop core algorithms for video generation and editing; Solve key issues like 'AI look', temporal consistency, and image quality; Explore and implement fine-grained control schemes for generated content; Reproduce and evaluate SOTA algorithms and adapt them for film scenarios; Collaborate with product, engineering, and content teams to convert algorithms into product features.
