Research Scientist, Real-Time DiT Video Models
WFA Digital Insight
The demand for AI experts in digital content creation has surged, with a 28% increase in remote job postings in 2025. As companies like Oddin pioneer interactive video content, the need for skilled research scientists with expertise in machine learning and computer vision has never been more pressing. With the global digital content market projected to reach
Job Description
About the Role
The Research Scientist position at Oddin is a unique opportunity to join a visionary team revolutionizing the way people create and experience digital content. As a research scientist, you will be responsible for designing, developing, and optimizing AI video generation models using diffusion techniques. Your primary focus will be on maintaining consistency, realism, and style in these models. You will work closely with other teams on large-scale video datasets, including human motion and gestures, facial expressions, and scene context. The role requires a strong research background in image or video synthesis, demonstrated by publications in top-tier conferences such as CVPR, NeurIPS, and ICCV.The day-to-day responsibilities of this position will involve experimenting with cutting-edge diffusion architectures for controllable and high-quality video synthesis. You will define robust validation strategies and implement custom evaluation metrics comparing synthetic vs. real gameplay. Staying on the bleeding edge of relevant literature and helping to align it with the company's roadmap will also be essential.
Oddin is part of the Realms Group, a parent company dedicated to pushing the boundaries of digital content creation. By joining this team, you will be part of a diverse group of innovators driven to redefine what's possible in generative content, moving from passive viewing to active participation and unlocking new creative frontiers across gaming, entertainment, education, and beyond.
What You Will Do
- Design, develop, and optimize AI video generation models using diffusion techniques.
- 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 and gestures, facial expressions, and scene context.
- Experiment with cutting-edge diffusion architectures for controllable and high-quality video synthesis.
- Define robust validation strategies and implement custom evaluation metrics comparing synthetic vs. real gameplay.
- Stay updated with the latest research and developments in the field, including publications in top-tier conferences.
- Align the latest research findings with the company's roadmap and goals.
- Collaborate with cross-functional teams to integrate AI-generated video content into various applications.
- Develop and maintain detailed documentation of research and development activities.
What We Are Looking For
- PhD in Computer Vision, Machine Learning, or a closely related field.
- Hands-on experience with research on video diffusion models.
- Strong research background in image or video synthesis, demonstrated by publications in top-tier conferences.
- Experience with real-time video generation is highly desirable.
- Proficiency in Python and ML frameworks such as PyTorch.
- Solid understanding of neural architectures or paradigms (CNNs, Transformers, diffusion models, autoregressive models, etc.).
- Excellent problem-solving skills and the ability to work in a team environment.
Nice to Have
- Experience with large-scale video dataset management and processing.
- Knowledge of human-computer interaction principles and their application in digital content creation.
- Familiarity with cloud-based services for scalable video processing and deployment.
Benefits and Perks
- Competitive salary and benefits package.
- Opportunity to work on cutting-edge technologies and contribute to the development of innovative digital content creation tools.
- Collaborative and dynamic work environment with a team of experienced professionals.
- Flexible remote work arrangements and a stipend for home office setup.
- Access to the latest research and development tools, as well as opportunities for professional growth and development.
- Comprehensive health insurance and retirement plan.
How to Stand Out
- Ensure your resume and cover letter highlight specific experiences with video diffusion models and AI-generated content.
- Prepare to discuss your research background and publications in top-tier conferences during the interview.
- Familiarize yourself with PyTorch and other ML frameworks commonly used in the industry.
- Be ready to provide examples of your problem-solving skills and experience working in team environments.
- Consider creating a portfolio that showcases your work in image or video synthesis and AI-generated content.
- Research the company's current projects and be prepared to discuss how your skills and experience align with their goals.
This is a remote position listed on WFA Digital, the platform for professionals who work from anywhere. Browse more remote jobs across all categories.