Computer Vision Engineer

Job Summary
We are seeking a highly skilled Computer Vision Engineer with expertise in 3D point cloud processing, SLAM (Simultaneous Localization and Mapping), and advanced AI integration to join our innovative team. The ideal candidate will design, optimize, and implement cutting-edge algorithms for real-time applications in both mobile and static environments. This role involves close collaboration with cross-functional teams and research partners to enhance our SpatialSense platform and push the boundaries of computer vision and machine learning technologies.

Key Responsibilities
Design and implement sophisticated algorithms focused on 3D point cloud processing, object recognition, and segmentation. You will be responsible for enhancing SLAM algorithms to ensure real-time performance in diverse environments. Integration of AI technologies such as Open3D and combined 2D+3D inference models will be critical to improving data analysis and visualization capabilities.

Collaboration is key in this role, as you will work closely with cross-functional teams to incorporate new features into the SpatialSense platform. You will also conduct research and development activities to explore and adopt novel techniques in computer vision and machine learning, ensuring the robustness and accuracy of applications across various operational conditions.

Your expertise will extend to designing and developing computer vision algorithms for object detection, classification, segmentation, and tracking. Optimizing these algorithms for NVIDIA hardware, including GPUs and Tensor Cores, is essential. You will collaborate with hardware engineers to leverage the latest NVIDIA platform capabilities, profile and benchmark performance, and identify bottlenecks to improve efficiency.

Implementation and deployment of algorithms will focus on maintaining real-time performance and scalability. Additionally, you will engage with research institutions and academic partners to stay at the forefront of state-of-the-art vision techniques and integrate these advancements into our solutions.

Required Qualifications
- Strong foundation in 3D point cloud processing, SLAM, point cloud registration, and camera-LiDAR calibration.
- Proven experience applying deep learning techniques to point cloud data.
- Proficiency with deep learning frameworks such as TensorFlow or PyTorch.
- Advanced programming skills in Python and C++.
- Hands-on experience with NVIDIA CUDA, cuDNN, and TensorRT for GPU acceleration.
- Solid understanding of core computer vision concepts including image processing, feature extraction, object detection, and segmentation.
- Familiarity with libraries such as OpenCV, PCL (Point Cloud Library), or Dlib.
- Experience in parallel computing and GPU programming is advantageous.
- Experience working with ROS (Robot Operating System) is highly preferred.
- Strong analytical and problem-solving abilities.
- Excellent communication skills and a collaborative approach to teamwork.

Preferred Qualifications and Benefits
While not explicitly listed, candidates with experience in parallel computing, GPU programming, and ROS will have a distinct advantage. The role offers the opportunity to work with cutting-edge NVIDIA hardware and collaborate with leading academic and research partners, providing a stimulating environment for professional growth and innovation.

---

This position is ideal for professionals passionate about advancing computer vision and AI technologies in real-world applications, particularly those who thrive in collaborative, research-driven environments. If you possess the required skills and are eager to contribute to next-generation spatial computing solutions, we encourage you to apply.