Human-Centric Modeling Intern

Summary

At Apple, new ideas have a way of becoming extraordinary products, services, and customer experiences very quickly. Bring passion for problem-solving and dedication to your job, and there's no telling what you could accomplish. We build technology that improves the lives of our customers worldwide. The Europe Vision Group (EVG) develops applied computer vision and machine learning to enrich human communication, from generative models and video diffusion to scene reconstruction and 3D human representations. Our team has delivered groundbreaking human-centric vision technologies used by millions worldwide, including Persona for Apple Vision Pro, Screen Distance or FaceTime Eye Contact. These innovations are the result of applied R&D that takes ideas from prototype to shipping product. We are seeking an R&D intern who is passionate about shaping the future of Apple products and excited to contribute to the next wave of transformative computer vision experiences.

Minimum Qualifications

Currently pursuing an MS or PhD degree in Computer Science, or a related field. At the end of the internship, you must return to school to continue your education or the internship must be the last requirement for you to graduate. Strong understanding of generative models and/or multi-modal foundation models. Strong understanding of neural rendering, 3D representations and Gaussian Splatting. Fluency in Python and Machine Learning Frameworks (i.e. PyTorch) is required. Excellent communication and collaboration skills. Demonstrable problem solving and analytical thinking abilities.

Preferred Qualifications

Hands-on experience with 3D generative models, image or video diffusion models, or vision foundation models. Track record of applied results, such as shipped or open-source projects, or publications at venues like CVPR, ECCV, ICCV, NeurIPS, ICLR or SIGGRAPH, is a plus. Availability for 6 months minimum is preferred. Industry experience is a plus.

Description

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 (multi-modal) algorithms that model humans in complex and diverse scenarios. * Human-centric multi-modal generative models * Human-centric video diffusion models * Human behavior modeling and simulation * World models and sequence models * 3D reconstruction of humans * Representation learning and spatial understanding * Face and body tracking * Human-object interaction * Advanced neural rendering techniques * Neural simulation techniques