Senior AI Vision Engineer

Our client, a global innovation center in Singapore focused on research and development in advanced mobility ecosystems, driving smarter urban living solutions for broader societal benefits.

What to Expect

• Work on deep learning for 2D/3D object recognition, segmentation, pose estimation, and human activity recognition.
• Develop and optimize AI models (CNNs, transformers) for sensor data in quality inspection.
• Apply deep learning to human activity recognition across video and other sensor types.
• Calibrate sensors for accurate data collection and preprocess images/sensor data for training.
• Test models on real-world car part datasets and document findings.

What You'll Bring

• Master's/Ph.D. in Engineering or related field with 5+ years of experience.
• Strong skills in object detection, segmentation (YOLO, Faster R-CNN, Mask2Former).
• Experience with human detection/activity recognition models (I3D, C3D).
• Bonus: Experience with 3D sensor data from head-mounted cameras.
• Solid understanding of data preprocessing, sensor calibration, and deep learning deployment.
• Extra points for patents, publications, or certifications in multimodal processing.