The ideal candidate will have an interest in producing new science to understand intelligence and technology to make computers more intelligent and an equal interest in taking new research findings in this area and implementing it toward production-ready problems.
Responsibilities
- Focus on computer vision tasks related to Structure from Motion (SfM) and visual localization problem
- Optimize the speed of existing models and improve the model pipeline performance
- Level up models and pipelines to support massive scale datasets with the robustness
- Solve challenging problems in the domain of SLAM, tracking, 3D reconstruction, localization, calibration automation, large-scale optimization, state estimation, etc.
- Analyze and improve the efficiency, accuracy, scalability, and stability of currently deployed systems
- Design and execution of algorithms
- Prototyping, building, and analysis of experimental systems
- Collaboration with and support of other researchers across various disciplines
- Communication of research agenda, progress, and results
Minimum Qualifications
- Currently has, or is in the process of obtaining, an MS or Ph.D. in the field of Computer Science, Computer Vision, Machine Learning, Robotics, Physics, or a related field
- Must obtain work authorization in country of employment at the time of hire and maintain ongoing work authorization during employment
- Understanding of statistical analysis of data and mathematical modeling
- Understanding of machine learning, artificial intelligence, quaternion transformation, 3D geometry, optimization, system building, or physics-based simulation
- Experience with deep learning frameworks like PyTorch
- Experience in C++ or Python
- Interpersonal experience: cross-group and cross-culture collaboration
Preferred Qualifications
- Experience in machine perception, geometric computer vision, including tracking, visual-inertial odometry, SLAM, large-scale structure from motion or relocalization technologies
- Experience in working with cameras and advanced imaging sensors, IMUs, magnetometers, and other sensors that can be used in this context
- Experience working on modern deep-learning methods for self-supervised learning, federated learning, video-understanding, GANs, reinforcement learning, graph neural networks, etc.
- Broad understanding of the entire machine vision pipeline from sensors to high-level algorithms
- Experience with privacy-aware algorithms for the 3D reconstruction and machine learning
- Proven track record of achieving significant results as demonstrated by grants, fellowships, patents, as well as first-authored publications at leading workshops or conferences such as CVPR, ECCV/ICCV, BMVC, NeurIPS, ICLR, ICRA, IROS, RSS or SIGGRAPH
- Demonstrated software engineer experience via work experience, coding competitions, or widely used contributions in open-source repositories (e.g., GitHub)