Middle/Senior Computer Vision Engineer (#3149)

N-iX is seeking a skilled Computer Vision Engineer to lead the development and deployment of an OCR system for the medical device.

This role focuses on optimizing OCR models to extract critical patient information from medication pouches, ensuring compliance with GDPR and performance on edge hardware.

You will collaborate with embedded engineers, data annotators, and QA teams to deliver a robust, low-latency solution for EU and global markets.

Key Responsibilities:

• OCR Model Development, Optimization & Fine-tune
• Optimize models for edge deployment (quantization, pruning, etc.)
• Design synthetic data pipelines to augment limited training datasets.
• Implement rule-based (regex) and ML-driven (NER) techniques to extract and validate crucial fields.
• Develop error-handling logic for OCR misreads (e.g., date format corrections).
• Conduct rigorous testing under real-world conditions (low-light, blur, layout variability).
• Document training pipelines, integration steps, and performance benchmarks.

Required Skills:

• Education: Master’s/PhD in Computer Vision, Machine Learning, or a related field.
• 3+ years in OCR model development (PaddleOCR, Tesseract, or EasyOCR).
• Proficiency in multilingual text recognition (Nordic languages preferred).
• Hands-on experience with edge deployment (NPU/GPU optimization, quantization).
• Strong Python skills with libraries like OpenCV, PyTorch, and spaCy.
• Experience in regulated industries (healthcare, pharmaceuticals - nice to have) 

Technical Skills:

• Regex-based post-processing for structured data extraction.
• Image preprocessing (noise reduction, deskewing, ROI detection).
• Familiarity with RKNN Toolkit, ONNX Runtime, or TensorRT.
• Familiarity with synthetic data generation (GANs, rule-based methods).

Soft Skills:

• Problem-solving in resource-constrained environments.
• Strong communication for cross-functional collaboration.