Skip to main content AIEngineer.careers AIEngineer.careers Real AI engineering roles. Top companies. Zero noise.
Browse Popular roles
Top locations
© 2026 AIEngineer.careers
Ingenjör at ManoMotion AB | AIEngineer.careers
Home / Jobs / IngenjörIngenjör Apply Now About the Role ManoMotion is seeking a Computer Vision Engineer to develop robust vision solutions combining AI/ML with traditional image processing and geometry. You will design complete systems, optimize for edge devices, and take technical ownership of customer integrations.
Responsibilities Design complete computer-vision solutions combining AI/ML, image processing, tracking, geometry, and rule-based algorithms. Develop algorithms for object detection, segmentation, motion analysis, pose estimation, and tracking. Build pre- and post-processing layers around AI models to improve accuracy and robustness. Analyze failure cases and decide on improvements via models, data, or system logic. Integrate trained models into real-time systems and optimize for latency, frame rate, and memory. Take end-to-end technical ownership of customer solutions from requirements to deployment. Use AI-assisted development tools like Cursor, Claude, ChatGPT, Copilot to accelerate work. Requirements Master's/PhD or equivalent in CS, CV, EE, Robotics, ML, or related field. 3+ years professional experience in computer vision or AI-based products. Strong knowledge of image processing, object detection, segmentation, tracking, geometry, and camera systems. Stockholm · SE · 11+ employees
ManoMotion is a deep-tech company that specializes in developing vision-based Physical AI technologies for human-hand tracking and gesture control. Its solutions are designed for various applications, including industrial safety, gesture-based human-machine interaction, and XR, using standard cameras found in smart devices and machines.
Report this listing
Understanding of deep learning, training, evaluation, and data management.
Proficiency in Python with OpenCV, NumPy, PyTorch, or TensorFlow.
Good C++ skills and experience with ONNX, TensorRT, CUDA, OpenVINO for deployment.
Experience developing real-time vision systems for edge devices.
Strong debugging and problem-solving skills, ability to work independently. Nice to Have Object tracking, temporal filtering, sensor fusion, multi-camera systems. Camera calibration, 3D geometry, depth estimation, pose estimation. NVIDIA Jetson or embedded GPU platforms. Industrial, robotics, automotive, safety, or HMI applications. Docker, CI/CD, cloud platforms, MLOps. Tech Stack Python CI/CD MLOps PyTorch TensorFlow TensorRT Docker C++ CUDA NumPy ONNX OpenCV OpenVINO