We are looking for an experienced Computer Vision Engineer to contribute to the development of the next generation of intelligent robotic technologies. In this role, you will help build core algorithms and software that power our automation platforms, collaborating with specialists across multiple engineering disciplines. You'll tackle real-world technical challenges involving perception, 3D understanding, and visual intelligence for industrial robotics.
Responsibilities
- Design and develop advanced algorithms for tasks such as 3D perception, image analysis, object recognition, tracking, and scene interpretation to enhance robotic capabilities.
- Build reliable and high-performing software modules that integrate computer vision functionality into robotic products.
- Work closely with cross-functional teams to experiment with new ideas, build prototypes, and transition research concepts into production-ready solutions.
- Keep up with emerging developments in computer vision and machine learning and evaluate their applicability to ongoing projects.
- Improve existing vision pipelines to achieve higher accuracy, reduce computational load, and support real-time operations.
- Perform comprehensive validation and stress testing to ensure algorithms remain robust under varied operating conditions.
- Prepare clear documentation covering system designs, implementation approaches, and testing methodologies.
What You Bring
- Master's Degree in a relevant discipline such as Computer Science, Electrical Engineering, or Robotics, along with 2+ years of hands-on experience building computer vision systems for real applications.
- Strong theoretical and practical knowledge of core computer vision methods, multi-view geometry, depth estimation, image-processing techniques, and classical ML.
- Strong Deep learning knowledge.
- Proven experience with camera calibration workflows, including intrinsics, stereo/multi-camera alignment, and calibration between cameras and robotic systems.
- Excellent programming skills in C++, Python, and CUDA, plus familiarity with common libraries like OpenCV, PCL, TensorFlow, and PyTorch.
- Hands-on experience with 3D reconstruction techniques (e.g., NeRF, Gaussian methods).
- Practical exposure to point cloud processing is a strong advantage.
- Ability to communicate complex ideas clearly and work effectively in a collaborative R&D environment.
- A creative, resourceful approach to solving complex perception and robotics problems.
