Sr. AI/ ML Engineer (OCR Solutions)

Sr. AI/ML Engineer (OCR Solutions)

~ Notice Period should be max. 1 month

Key Responsibilities:

• Build and improve OCR solutions capable of handling diverse languages, scripts, and complex layouts.
• Train, fine-tune, and deploy machine learning models for text recognition across

  multiple languages and character sets

  , including low-resource languages.
• Evaluate & Improve Accuracy: Implement model evaluation metrics to continuously improve the accuracy and performance of OCR systems.

• 5Scaling OCR Solutions:

  Design scalable OCR models that can efficiently handle large volumes of data in real-time applications. Focus on optimizing model performance for both cloud-based and edge environments.
• Collaboration: Work with cross-functional teams, including product managers, software engineers, and UX designers, to integrate OCR functionality into products.

• Deployment & Scalability:

  Ensure that the OCR models are scalable and optimized for deployment in production environments (cloud and edge devices). Implement and manage CI/CD pipelines for smooth deployment.

Requirements:

• Experience in AI/ML engineering with at least 3 years of experience in building OCR solutions.
• Expertise: Strong knowledge of OCR technologies, including

  Tesseract, EasyOCR, PaddleOCR, or custom deep learning-based OCR systems

• Languages: Experience with multiple languages and character sets

  (e.g., Latin, Cyrillic, Chinese, Japanese, Arabic, Devanagari, etc.)

• Deep Learning: Proficiency with machine learning frameworks like

  TensorFlow, PyTorch, Keras, or MXNet

• NLP Skills: Experience in natural language processing (NLP) techniques for post-processing OCR outputs.
• Programming Languages: Strong programming skills in Python and familiarity with ML libraries (scikit-learn, OpenCV, etc.).
• Proven experience in scaling AI/ML models for production environments and containerizing applications using Docker for easier deployment and scalability.
• Cloud & DevOps: Experience deploying OCR models in cloud environments (AWS, GCP, or Azure) and working with CI/CD pipelines.

Preferred Qualifications:

• Experience with low-resource or less common languages.
• Familiarity with handwriting recognition and scene text recognition.
• Knowledge of transformer-based models like Vision Transformers (ViTs) or hybrid approaches.
• Experience with Docker, Kubernetes, and container orchestration for AI/ML model deployment.
• Contributions to open-source OCR projects