2022 Call for Interns, Creative Vision

The Creative Vision Team at Snap Research seeks highly motivated PhD students in Computer Vision for 12-16 week internships in multiple locations in the US and internationally

Apply Email us

Snap Inc. is a camera company. We believe that reinventing the camera represents our greatest opportunity to improve the way people live and communicate. Our products empower people to express themselves, live in the moment, learn about the world, and have fun together.

At Creative Vision, we strive to build an artificial creative mind and bring it into every device, unlocking and enhancing creativity of our users and creators.

At CVPR'2021 we organized a Tutorial on Creativity, which shows our 2020-2021 works, many of which done by our interns.

In our pursuit, we believe, four components are necessary:

  • Understanding Humans: 3D pose & geometry of face, body, hand, clothes
  • Understanding the World: recognition, segmentation, 3D reconstruction, referential-languages, scene understanding
  • Tools for Creativity: 2D and 3D image and video synthesis, animation, manipulation, stylization, emotion explanation
  • Efficient Algorithms and Architectures: faster, smaller models and more accurate inference

If these topics sound exciting for you, you have top conference first author publications, join us for the spring, summer or fall in 2022. You’ll work towards a publication at a top conference with a possibility to impact Snap products!

Please email the team directly or submit your application and select the Creative Vision team.

Team

Hsin-Ying Lee

Image and video synthesis, stylization, manipulation

Jian Ren

Video synthesis, animation, NN compression & quantization, transformers for vision

Menglei Chai

Graphics, neural rendering, physics-based simulation, object centric ML

Kyle Olszewski

Graphics, neural rendering, object manipulation, novel view synthesis, object centric ML

Sergey Tulyakov

2D and 3D image and video synthesis, animation, manipulation, self-supervized learning

Panos Achlioptas

Multi-modal learning, 3D vision, referential-language learning, affective computing, emotions in art

Aliaksandr Siarohin

Generative Modeling, self-supervised learning, image animation, video generation