Head of Research, AI
avra
AWSNode.jsPythonPyTorch
Research Scientist, Real-Time DiT Video Models
Oddin.gg
full-time
Posted on:
Origin: • 🇺🇸 United States
Visit company websiteJob Level
Mid-LevelSenior
About the role
- Design, develop, and optimize AI video generation models using diffusion techniques, focusing on consistency, realism, and style
- Develop and implement state-of-the-art algorithms for generating video content
- Work closely with other teams on large-scale video datasets including human motion, gestures, facial expressions, and scene context
- Experiment with diffusion architectures for controllable and high-quality video synthesis
- Define validation strategies and implement custom evaluation metrics comparing synthetic vs. real gameplay
- Stay up-to-date with relevant literature and align findings with product roadmap
Requirements
- PhD in Computer Vision, Machine Learning, or a closely related field
- Hands-on experience with research of video diffusion models
- Strong research background in image or video synthesis with publications at top-tier conferences (CVPR, NeurIPS, ICCV, Siggraph, ICML)
- Experience with real time video generation is a plus
- Proficiency in Python and ML frameworks such as PyTorch
- Solid understanding of neural architectures or paradigms (CNNs, Transformers, diffusion models, autoregressive models)
- Familiarity with current literature (CVPR, NeurIPS, ICML, ICCV)
