Research Scientist Intern, Machine Learning, Human Motion Models (PhD)

Description

The Reality Labs (RL) Research team brings together a world-class team of researchers, developers, and engineers to create the future of AR and VR, which together will become as universal and essential as smartphones and personal computers are today. We are developing all the technologies needed to enable breakthrough AR glasses and VR headsets, working at the intersection of Computer Vision, Computer Graphics, and Machine Learning. The Virtual Humans team in Zurich, CH works on cutting-edge research and development focusing on virtual people and presence. Our internships are twelve (12) to sixteen (16) to twenty four (24) weeks long and we have various start dates throughout the year. Research Topics: * Character animation synthesis, editing, retargeting, and stylization * Human motion reconstruction, estimation, and analysis * Human-scene interaction understanding and modelling * Efficient and realistic physics simulation of human motion * Novel input and interfaces for human motion synthesis, control, and editing * Evaluation of avatar systems

Responsibilities

Prototyping, building, and analysis of novel research ideas Design and execution of algorithms, planning and analysis of experiments Collaboration with and support of other researchers across various disciplines Communication of research agenda, progress and results

Qualifications

Currently has, or is in the process of obtaining, a PhD in Computer Vision, Computer Graphics, Robotics, Machine Learning, Human-Computer Interaction, or related fields Understanding of machine learning, 3D geometry, optimization, and system building Experience with deep learning frameworks like PyTorch Interpersonal skills: cross-group and cross-culture collaboration Must obtain work authorization in the country of employment at the time of hire, and maintain ongoing work authorization during employment Intent to return to degree-program after the completion of the internship 2+ years experience in one or more of the following areas: human motion synthesis, editing, and retargeting - human motion perception, reconstruction, and analysis - generative modelling of human motion - reinforcement learning Proven track record of achieving results as demonstrated in accepted papers at top vision, graphics, robotics related journals and conferences such as CVPR, ECCV/ICCV, SIGGRAPH, NeurIPS, etc