Join our team and build your career with us
Arabot is MENA’s #1 semantic automation platform that brings AI and service fulfillment together to get the job done. We are a fast-growing startup with lots of exciting business and technical challenges coming every day solved by motivated and bright minds. On joining our team, you will enjoy competitive salary and benefits, flexible working hours, remote work policy, great environment and culture!
Job Summary:
We are seeking a highly skilled Senior AI Engineer specializing in Arabic OCR and Machine Vision to join our innovative team. The ideal candidate will have deep expertise in computer vision, deep learning, and natural language processing with specific focus on Arabic text recognition and document understanding systems.
Job Description:
Design, develop, and deploy state-of-the-art OCR systems for Arabic text recognition with high accuracy across various fonts, styles, and document formats
Build and optimize machine vision pipelines for document analysis, layout detection, and information extraction
Develop synthetic data pipelines to overcome the scarcity of labeled Arabic document datasets
Research and implement deep learning architectures (CNNs, RNNs, Transformers) for text detection and recognition tasks
Develop solutions for handling Arabic script complexities including diacritics, ligatures, and bidirectional text
Create and maintain training datasets, perform data augmentation, and implement quality assurance processes
Optimize models for production deployment, ensuring low latency and high throughput
Collaborate with cross-functional teams to integrate OCR capabilities into existing products and platforms
Stay current with latest research in computer vision and OCR, and apply cutting-edge techniques to solve business problems
Mentor junior team members and contribute to technical documentation and knowledge sharing
Required Qualifications:
Bachelor’s or Master’s degree in Computer Science, Engineering, Mathematics, or related field
5+ years of professional experience in AI/ML engineering with at least 3 years focused on computer vision or OCR
Proven track record of deploying OCR or machine vision systems in production environments
Strong proficiency in Python and deep learning frameworks (TensorFlow, PyTorch, or Keras)
Extensive experience with computer vision libraries (OpenCV, PIL, scikit-image)
Deep understanding of OCR architectures (CRNN, EAST, Transformer-based models like TrOCR, Donut)
Experience with text detection algorithms (CTPN, EAST, DBNet, PSENet)
Knowledge of Arabic NLP and understanding of Arabic script characteristics
Familiarity with containerization (Docker, Kubernetes) and CI/CD pipelines
Experience with NVIDIA TensorRT or ONNX Runtime
Strong background in mathematics, linear algebra, and statistics
Preferred Qualifications:
Experience with diverse Arabic calligraphic styles (e.g., Naskh, Ruq’ah)
Knowledge of document understanding models (LayoutLM, DocFormer)
Experience with model optimization techniques (quantization, pruning, knowledge distillation)
Familiarity with MLOps practices and tools (MLflow, Kubeflow, Weights & Biases)
Please submit your CV highlighting your relevant experience in Arabic OCR and Machine Vision. Include links to any relevant projects, publications, or GitHub repositories.
