Description
We are seeking a highly skilled AI Engineer specializing in AI detection and Generative AI for advanced imaging applications at submicron scales, including medical and industrial applications. The ideal candidate will have expertise in 2D/3D segmentation and detection for microscopic objects under X-ray CT scans and experience in generating synthetic X-ray images using Generative AI technologies.
Key Responsibilities
- AI Detection & Segmentation: Develop and optimize advanced 2D and 3D detection algorithms along with point cloud segmentation for detecting microscopic objects in X-ray CT scan data
- Generative AI Implementation: Design and implement GenAI models to create high-quality synthetic X-ray images for training data augmentation and research purposes
- Model Development: Build and fine-tune deep learning models for submicroscopic image analysis, including YOLO architectures, U-Net, transformer-based segmentation models, and Stable Diffusion architectures for GenAI
- Research & Innovation: Stay current with latest developments in computer vision and generative AI, implementing cutting-edge techniques
- Quality Assurance: Ensure AI models meet microscopic imaging standards and regulatory requirements
- Collaboration: Work closely with researchers, field professionals, and research teams to understand detection and GenAI research needs
Compensation Package:
- Competitive tax-free salary
- Free on-campus housing
- Health insurance
- Round trip ticket
- 22 days of annual vacation
- Additional benefits
- Remote work possibility
About CREST:
The Center for Renewable Energy and Storage Technologies (CREST) at KAUST aims to develop renewable energy and storage technologies that help Saudi Arabia achieve its environmental and economic goals. Through strategic partnerships, cutting-edge research, and workforce training, the center will spearhead the prototyping and eventual commercialization of renewable energy and storage solutions that secure the Kingdom’s industrial competitiveness and empower its ambition to expand into new sustainability-centered economic sectors. CREST aims to focus on home-grown technologies, invented at KAUST.
About KAUST:
KAUST is located on the shores of the Red Sea near Jeddah, Saudi Arabia, and welcomes exceptional students, researchers, and faculty from around the world. Our university is internationally diverse with over 100 Nationalities living and working on campus. KAUST boasts world-class equipment, research and recreational facilities, and computational resources. It is the leading university in citation per faculty according to the QS Rankings. Further information can be found at www.kaust.edu.sa.
Qualifications
- Education: Ph.D. or M.S. in Computer Science, AI, Computer Vision, or related field
- Experience: 3+ years in computer vision and deep learning, with specific focus on microscopic imaging, generation, and 2D/3D detection along with point cloud processing
- Required Technical Expertise:
○ Deep Learning Frameworks: PyTorch, TensorFlow
○ Computer Vision Libraries: OpenCV, scikit-image
○ Object Detection: YOLO family (v5, v7, v8, v11), Faster R-CNN, RetinaNet
○ Image Processing: Classical and deep learning-based approaches
○ Version Control: Git
○ ML Operations: Docker, MLflow
○ Expertise in 2D/3D image segmentation, detection, and Stable Diffusion techniques (U-Net, V-Net, DeepLab)
○ Strong experience with Generative AI models (GANs, VAEs, Diffusion Models)
○ Proficiency in imaging formats (DICOM, NIfTI) and standards
○ Experience with X-ray CT scan analysis and processing
○ Strong Python programming skills with scientific computing libraries (NumPy, SciPy)
○
Preferred Qualifications
- Publications in top-tier computer vision or AI conferences (CVPR, ICCV, NeurIPS, MICCAI)
- Experience with Stable Diffusion, DALL-E, or similar generative models for imaging applications
- Knowledge of imaging physics and CT reconstruction principles
- Experience with cloud-based ML platforms (AWS SageMaker, Google Cloud AI)
- Familiarity with imaging device standards and quality assurance processes
- Experience with annotation tools and dataset curation for imaging applications
Technical Stack
- Deep Learning: PyTorch (primary), TensorFlow, Keras
- Computer Vision: OpenCV, scikit-image, ITK, SimpleITK
- Generative AI: Stable Diffusion, GANs, VAEs, Diffusion Models
- Imaging Tools: DICOM handling, 3D Slicer, ImageJ
- MLOps: Docker, Kubernetes, MLflow, DVC
- Programming: Python, CUDA, Git
Application Instructions
- Applications must be submitted through PlutoEdu (https://www.plutoedu.com/form/792303151)
- Please do not send your CV to the Professor through e-mail or LinkedIn account. Candidates who do so will be excluded.