This position requires highly-motivated individuals who want to join us in the fast-moving field of large-scale models for human-centric 3D representations. You will be responsible for developing, implementing, evaluating, and improving computer vision and GenAI algorithms that model photorealistic humans in complex and diverse scenarios. Potential internship areas: * Human-centric video diffusion models * 3D reconstruction of humans * Human-centric generative models * Face and body tracking * Human-object Interaction * Advanced neural rendering techniques * Neural simulation techniques * Power-efficient deep learning Strong understanding of modern machine learning techniques (e.g., generative, multi-modal, and foundational models, video understanding, and self-supervised learning). Strong understanding of modern approaches for 3D reconstruction and rendering (e.g., MVS, NeRF, Gaussian Splatting). Fluency in Python and Machine Learning frameworks (e.g. PyTorch) is required. Excellent communication and collaboration skills. Good problem solving and analytical thinking abilities. Working towards a MSc or PhD degree in Computer Science or a related field. PhD students are preferred for research-focused internships. At the end of the internship, you must return to university to continue your education, or the internship must be the last requirement for you to graduate. Hands-on experience with image or video diffusion models, 3D generative models, Gaussian splatting, or vision foundation models. Hands-on experience with human modeling algorithms (e.g., skeletal tracking, body shape and pose models, hair and garment modeling). Publication record at top conferences such as CVPR, ECCV, ICCV, NeurIPS or SIGGRAPH is a plus. Availability for 6 months minimum is preferred. Industry experience is a plus.