**Summary:** The Reality Labs team at Meta is looking for Computer Vision Engineers to support our engineering teams as we build towards our goal to transform the way people come together to interact, work and play.We explore, develop and deliver cutting-edge technologies that serve as the foundations for the current and future Reality Labs products, such as Oculus headsets, AR and Smart glasses, and AI assistants. We are committed to driving the state-of-the-art forward through relentless innovation. From Visual Localization, SLAM, 3D reconstruction, Scene Understanding, to Vision Language Models, our team is focused on taking new technologies from early concept to the product level while iterating, prototyping, and realizing the human value and new experiences they open up. **Required Skills:** Research Scientist, Computer Vision (Vision Language Models for Spatial AI) Responsibilities: 1. Conduct applied research to advance the State of the Art in 3D Computer Vision (Depth Estimation, 3D Spatial Reasoning, Segmentation) and Vision Language / Multimodal Models. 2. Apply research to advance Meta's MR and AR products and Spatial Computing experiences. 3. Consistently and sustainably advance the state of the art for your problem, including setting and executing against roadmaps for 6-month plus timeframes. 4. Collaborate with different cross-functional teams across the globe in research and product. 5. Present the outcomes of the research findings as papers in world class conferences in the area of CV/ML and Graphics. **Minimum Qualifications:** Minimum Qualifications: 6. PhD in Computer Science or a related field with published projects in the fields of machine learning, deep learning and/or computer vision 7. Proven development skills in Deep Learning, working with PyTorch or TensorFlow 8. Experience developing computer vision algorithms or infrastructure in Python or C/C++ 9. Experience in one or more of the following areas: deep learning, Computer Vision, AR/VR, 3D Vision, Robotics, Machine Learning or artificial intelligence 10. First-authored publications at peer-reviewed conferences, e.g. CVPR, ECCV, ICCV, NeurIPS, SIGGRAPH **Preferred Qualifications:** Preferred Qualifications: 11. Experience solving complex problems and comparing alternative solutions, trade-offs, and broad points of view to determine a path forward 12. Experience with CPU/GPU and mobile optimization 13. Industry experience working on projects on Vision Language Models, Semantic Understanding (segmentation or semantic keypoints), depth estimation, or feed-forward 3D Reconstruction **Industry:** Internet