Kinetix is a start-up founded in 2020, specializing in artificial intelligence and 3D animation technologies. In collaboration with motion capture studios and highly-skilled actors and performers, we have built an extensive proprietary dataset of human motions rendered in various virtual scenes with an in-house synthetic data generation pipeline. Leveraging this dataset, we develop AI tools for character motion control in video diffusion models, as well as human pose estimation models to extract animations from videos.

Our R&D team is seeking an intern to contribute to our 3D animation technologies. With the support of our research engineers in AI and 3D, you will have the opportunity to work on one or more of the following projects:

• Human pose estimation (or “Video-to-Animation”): train new models to improve our body and hand pose estimation, as well as facial animation technologies;

• Retargeting: develop 3D algorithms and optimization techniques to adapt recorded motions to characters with varying heights and body shapes while preserving motion semantics;

• Animation post-processing: design methods to enhance the quality and realism of AI-generated or extracted animations. Typical use cases include reducing foot sliding to improve ground interaction, and removing self-intersections of the body mesh;

• Human motion synthesis: generate human motions from various inputs, such as text prompts or start/end pose.

Depending on your background, you will have the opportunity to focus on either algorithmic tasks (retargeting, animation post-processing) or on AI-related tasks.

You are a student in applied mathematics or machine learning, ideally with experience in Python, PyTorch, and Blender. Knowledge in computer vision and skeletal animation is a plus.

• Initial technical interview with our Head of AI;

• Second call with the CTO, who will answer any questions you may have about the company.