R&D Data Intern, Kinetix

• Given the multidisciplinary nature of this project and the variety of tasks involved, we welcome applications from students with diverse backgrounds, including software engineering, AI/data engineering or science, applied mathematics, and Unreal Engine development

Desirable

• Data acquisition: define future needs for motion data and help prepare motion capture sessions with our partners
• Data cleaning: assess the quality of recorded motions and develop tools to automate the detection of faulty animations
• Data augmentation: improve our retargeting methods (3D algorithms used to adapt recorded motions to characters of various heights and body shapes)
• Human body modeling: enhance the realism of our human body model
• Synthetic data generation: propose and implement new features for our synthetic data pipeline in Unreal Engine, aiming to reduce the gap between our synthetic data and real-world videos (e.g., clothes simulation)
• Data processing: build processing and filtering pipelines for our video diffusion model projects (e.g., with AI-based aesthetic score prediction and video captioning)

• Initial technical interview with our Head of AI
• Second call with the CTO, who will answer any questions you may have about the company