About the Role
We are seeking a Senior Software Engineer for Dense Reconstruction to join our team in Guangzhou, China. This role involves developing advanced algorithms and software for 3D dense reconstruction from various sensor inputs, primarily focusing on computer vision and potentially leveraging machine learning. You will be instrumental in creating highly detailed and accurate 3D models of environments and objects, which are critical for applications like robotics, autonomous systems, digital twins, and virtual reality. The successful candidate will work on optimizing these complex algorithms for performance and scalability on NVIDIA hardware.
Responsibilities
- Design and implement cutting-edge algorithms for dense 3D reconstruction.
- Develop and optimize software for processing large-scale sensor data (e.g., from cameras, depth sensors).
- Research and integrate machine learning techniques to improve reconstruction quality and efficiency.
- Collaborate with research teams to transfer state-of-the-art algorithms into production.
- Ensure software quality, performance, and robustness.
- Contribute to the architecture and design of reconstruction pipelines.
Requirements
- BS/MS/PhD in Computer Science, Robotics, Computer Vision, or a related field.
- 5+ years of experience in software development with a focus on 3D reconstruction or computer vision.
- Strong programming skills in C++ and Python.
- Expertise in computer vision libraries (e.g., OpenCV) and 3D geometry.
- Experience with deep learning frameworks (TensorFlow, PyTorch) for vision tasks.
- Familiarity with GPU programming (CUDA) for performance acceleration.
Qualifications
- Experience with real-time 3D reconstruction systems.
- Knowledge of photogrammetry and multi-view stereo.
- Publications in relevant conferences (e.g., CVPR, ICCV, ECCV).
Benefits
Competitive salary, comprehensive health benefits, retirement plans, paid time off, and opportunities for professional growth.