Middle/Senior Computer Vision Engineer

6 Months ago • 3-8 Years

Research Development

Job Description

N-iX is seeking a skilled Computer Vision Engineer to lead the development and deployment of an OCR system for medical devices. This role focuses on optimizing OCR models to extract patient information from medication pouches, ensuring GDPR compliance and performance on edge hardware. Responsibilities include OCR model development and optimization for edge deployment (quantization, pruning), designing synthetic data pipelines, implementing rule-based and ML-driven techniques for data extraction and validation, developing error-handling logic, conducting real-world testing, and documenting pipelines and benchmarks. Collaboration with embedded engineers, data annotators, and QA teams is required to deliver a robust, low-latency solution for EU and global markets.

Good To Have:

Experience in regulated industries
Familiarity with RKNN Toolkit, ONNX Runtime, or TensorRT
Familiarity with synthetic data generation

Must Have:

3+ years in OCR model development
Proficiency in multilingual text recognition
Edge deployment experience (NPU/GPU)
Strong Python skills (OpenCV, PyTorch, spaCy)
Master's/PhD in relevant field
Regex-based post-processing
Image preprocessing

Perks:

Flexible working format
Competitive salary
Personalized career growth
Professional development tools
Education reimbursement
Corporate events

Add these skills to join the top 1% applicants for this job

open-cv

computer-vision

python

pytorch

opencv

cross-functional-collaboration

quality-control

cross-functional

game-texts

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.

We offer:

Flexible working format - remote, office-based or flexible
A competitive salary and good compensation package
Personalized career growth
Professional development tools (mentorship program, tech talks and trainings, centers of excellence, and more)
Active tech communities with regular knowledge sharing
Education reimbursement
Memorable anniversary presents
Corporate events and team buildings
Other location-specific benefits