Computer Vision Research Scientist

1. Own a core area of our reconstruction stack and set its technical direction
2. Advance 3D visual representations, optimizing them for on-device delivery and representation
3. Develop image composition and correction techniques
4. Lead generative quality improvement for real-world capture
5. Optimize models for on-device inference under hard compute, memory, latency, thermal, and power constraints, and partition work between device and cloud
6. Define image quality gates
7. Own training data strategy,
8. Partner with product and platform teams to take prototypes through dogfooding and experimentation to shipped features
9. Shape the technical roadmap for your area and influence it across organizational boundaries
10. Deliver production-quality code, review others’ work, and raise the engineering bar

1. Bachelor’s degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience
2. PhD in Computer Science, Electrical Engineering, Robotics, Applied Math, or a related field with a computer vision, graphics, or ML focus - or equivalent practical experience
3. 6+ years building production computer vision or graphics systems
4. Deep expertise in geometric vision: SfM, SLAM/VIO, multi-view stereo, calibration, bundle adjustment, or learned depth
5. Proven experience training and deploying deep learning models (PyTorch or equivalent)
6. Expert-level C++ and strong Python
7. Demonstrated record of taking research from prototype to shipped product

Preferred Qualifications:

Preferred Qualifications:

1. Hands-on experience with 3D scene representations
2. Track record of technical leadership setting direction, mentoring, and driving multi-team efforts
3. Experience with generative image and video models
4. Strong publication record at top-tier venues (CVPR, ICCV, ECCV, NeurIPS, SIGGRAPH, 3DV)
5. Experience with camera ISP pipelines, computational photography, or multi-sensor fusion