Meta AR/VR Job | Research Scientist Intern, Video Compression (PhD)

Job(岗位): Research Scientist Intern, Video Compression (PhD)

Type(岗位类型): Computer Vision | Machine Learning, Research

Citys(岗位城市): Redmond, WA

Date(发布日期): Before 2021-12-14


Facebook Reality Labs Research (FRLR) brings together a world-class, cross-discipline R&D team with the shared goal of developing the next generation of AR and VR technologies. The Surreal Vision team is looking for the next generation of scientists and engineers to tackle the most ambitious problems in machine perception at our research location in Redmond, WA.

The primary role of this internship is to conduct research on multi-stream video compression for AR/VR applications.

Our internships are twelve (12) to twenty four (24) weeks long and we have various start dates throughout the year.


Currently has, or is in the process of obtaining, a PhD in the field of compression, or a related field

Experience in implementing compression algorithms

Interpersonal experience: cross-group and cross-culture collaboration

Must obtain work authorization in country of employment at the time of hire, and maintain ongoing work authorization during employment

Must be available for 3 month to 6 month internship between January 1, 2022 and December 31, 2022

Experience with C++ or Python

Strong foundational knowledge of compression and information theory


Analyzing and improving existing video compression techniques for multi-camera devices

Exploring emerging compression techniques for existing AR/VR datasets

Prototyping, building, and analysis of experimental systems

Collaboration with and support of other researchers across various disciplines

Communication of research agenda, progress and results

Additional Requirements(额外要求)

Intent to return to degree-program after the completion of the internship

Experience in any of the following research focuses: 3D video compression, ML-based compression, joint source channel coding

Strong track record of cross-disciplinary research work across computer vision, machine learning, and compression

Strong publication track record in one or more of the following conferences: IEEE Transactions on Information Theory, ISIT, CVPR, ICML, ICCV, NeurIPS