Research Scientist Intern, 3D Computer Vision/Machine Learning

Facebook's mission is to give people the power to build community and bring the world closer together. Through our family of apps and services, we're building a different kind of company that connects billions of people around the world, gives them ways to share what matters most to them, and helps bring people closer together. Whether we're creating new products or helping a small business expand its reach, people at Facebook are builders at heart. Our global teams are constantly iterating, solving problems, and working together to empower people around the world to build community and connect in meaningful ways. Together, we can help people build stronger communities - we're just getting started.


The Facebook Reality Labs team at Facebook is helping more people around the world come together and connect through world-class Augmented, Mixed and Virtual Reality hardware and software. With global departments dedicated to AR/VR research, computer vision, haptics, social interaction, and more, we are committed to driving the state-of-the-art forward through relentless innovation. AR and VR potential to change the world is immense -- and we're just getting started. 4DAI is seeking Research Engineer Interns to develop next-generation map-building algorithms. As a Research Engineer Intern, you will help us bring the best of 3D map building technology to Facebook AR/VR's products.
At Facebook Reality Labs, the XR Map Building team explores, develops, and delivers new cutting-edge technologies for 3D map building from large-scale and heterogeneous image data sources that serve as the foundation of current and future AR/VR products. Our team is addressing a variety of technical challenges in the areas of Structure-from-Motion, SLAM, 3D surface reconstruction, visual relocalization, large-scale bundle adjustment, map alignment, semantic scene modeling, and related domains. We're looking for candidates who share a passion for exploring and solving complex, challenging problems at the intersection of CV/ML and 3D reconstruction.

Required Skills

  • Research, develop, and implement computer vision algorithms to improve the capability, robustness, or speed of algorithms related to sparse 3D mapping, dense 3D modeling, or visual relocalization. A special emphasis is placed on large-scale modeling.
  • Collaborate with and support other engineers/researchers across various disciplines and teams.
  • Communicate the research project agenda, projects, and results.

Minimum Qualification

  • Currently has, or is in the process of obtaining, a PhD degree with a specialization in computer vision.
  • Available for an internship between January 1, 2022 and December 31, 2022.
  • Strong domain knowledge in one or more of the following fields: 3D reconstruction (Structure from Motion or SLAM), multi-view geometry, visual features in computer vision, object recognition, bundle adjustment, optimisation, (semi-, weakly-, self-supervised) machine learning, image processing, computational geometry, robotics, tracking, or sensor fusion.
  • 1 year proficient experience in C/C++ and/or Python.
  • Ability to communicate complex research in a clear, precise, and actionable manner.
  • Must obtain work authorization in the country of employment at the time of hire and maintain ongoing work authorization during employment.

Preferred Qualification

  • Publications in top computer vision conferences (e.g., CVPR, ICCV, ECCV, ICLR, IROS, 3DV, etc.) or journals.
  • Software engineering experience (via an internship, work experience, coding competitions, etc). Examples include but are not limited to: 2+ years of C/C++/Python programming in industry, experience of using open-source libraries (PyTorch, OpenCV, OpenGL, etc.), active contributions to a GitHub project, and any other projects or hackathons.
  • Research experience in 3D reconstruction (e.g., processing heterogeneous imagery, handling scene symmetries, achieving scalable and robust image matching, scaling bundle adjustment, applying machine learning / deep learning in the multi-view geometry domain).
  • Intent to return to degree-program after the completion of the internship.


Facebook is proud to be an Equal Opportunity and Affirmative Action employer. We do not discriminate based upon race, religion, color, national origin, sex (including pregnancy, childbirth, or related medical conditions), sexual orientation, gender, gender identity, gender expression, transgender status, sexual stereotypes, age, status as a protected veteran, status as an individual with a disability, or other applicable legally protected characteristics. We also consider qualified applicants with criminal histories, consistent with applicable federal, state and local law. Facebook is committed to providing reasonable accommodations for candidates with disabilities in our recruiting process. If you need any assistance or accommodations due to a disability, please let us know at