Computer Vision Engineer- Kolkata(Ruby)

We are looking for a skilled and solution-oriented Computer Vision Engineer to design, develop, deploy, and maintain computer vision and AI-based systems for manufacturing, quality control, warehouse, security, and operational automation. The candidate will work on real-time camera-based applications such as object detection, OCR, product and packaging inspection, vehicle and container monitoring, counting systems, defect detection, process compliance, and automated data capture.The role requires hands-on experience in Python, OpenCV, deep learning frameworks, camera integration, edge devices, and production deployment.

Key Responsibilities

1. Computer Vision Development

• Develop computer vision solutions for object detection, image classification, segmentation, tracking, OCR, and anomaly detection.
• Build systems for packaging inspection, bag counting, label verification, defect identification, and process monitoring.
• Train, fine-tune, test, and optimize deep learning models using real operational data.
• Prepare and manage image and video datasets, including annotation, augmentation, cleaning, and validation.
• Evaluate model performance using appropriate accuracy, precision, recall, F1-score, and inference-speed metrics.

2. Camera and Hardware Integration

• Integrate industrial cameras, IP cameras, lenses, sensors, lighting systems, and edge-computing devices.
• Configure camera angles, resolution, exposure, focus, frame rate, lighting, and image-capture conditions.
• Deploy computer vision applications on Raspberry Pi, NVIDIA Jetson, local servers, cloud servers, or industrial computers.
• Troubleshoot camera connectivity, network issues, hardware failures, image-quality problems, and performance bottlenecks.

3. OCR and Image Processing

• Develop OCR-based solutions for reading batch numbers, dates, labels, barcodes, QR codes, printed text, and packaging information.
• Apply image-processing techniques such as resizing, thresholding, denoising, contrast enhancement, edge detection, and perspective correction.
• Improve OCR accuracy for different fonts, lighting conditions, packaging materials, and camera positions.
• Integrate OCR results with databases, reports, dashboards, and business applications.

4. System Development and Deployment

• Develop backend APIs and services using Python frameworks such as FastAPI or Flask.
• Integrate computer vision applications with MySQL, PostgreSQL, SQL Server, or other databases.
• Store images, videos, model outputs, timestamps, user actions, and inspection results securely.
• Deploy applications on on-premises servers, cloud platforms, and edge devices.
• Implement real-time alerts, logs, dashboards, automated reports, and exception notifications.
• Maintain proper version control, deployment documentation, and model versioning.

5. Production Support and Improvement

• Monitor deployed systems and ensure continuous operational availability.
• Analyse false detections, missed detections, and system failures.
• Retrain and improve models based on new images, products, packaging formats, and production conditions.
• Optimize models for faster inference and reduced hardware requirements.
• Conduct regular system health checks, backup verification, and preventive maintenance.
• Provide technical support to factory, quality, production, IT, and operations teams.

6. Project Coordination

• Understand business requirements and convert them into practical computer vision solutions.
• Conduct site surveys to assess camera placement, lighting, network, hardware, and operational requirements.
• Coordinate with internal departments, hardware vendors, software vendors, and implementation partners.
• Prepare requirement documents, technical architecture, process flows, test cases, user manuals, and deployment documents.
• Conduct user acceptance testing and provide training to end users.
• Ensure projects are completed within the defined scope, timeline, and quality standards.

Required Technical Skills

• Strong programming knowledge in Python.
• Hands-on experience with OpenCV, NumPy, Pandas, and image-processing libraries.
• Experience with deep learning frameworks such as PyTorch, TensorFlow, or Keras.
• Knowledge of object detection models such as YOLO, Faster R-CNN, SSD, or similar architectures.
• Experience with OCR tools such as Tesseract, EasyOCR, PaddleOCR, or cloud-based OCR services.
• Understanding of image classification, object tracking, segmentation, and anomaly detection.
• Experience with camera integration, RTSP streams, IP cameras, USB cameras, and video processing.
• Knowledge of REST APIs, FastAPI, Flask, or similar backend frameworks.
• Working knowledge of SQL databases.
• Familiarity with Linux, Windows Server, Docker, Git, and basic networking.
• Experience deploying models on Raspberry Pi, NVIDIA Jetson, GPU servers, or other edge devices.
• Understanding of model optimization techniques such as ONNX, TensorRT, quantization, or pruning.

Educational Qualification

• B.Tech / B.E. / M.Tech / M.E. in Computer Science, Information Technology, Electronics, Electrical Engineering, Artificial Intelligence, Data Science, or a related discipline.
• Candidates with relevant certifications and strong practical project experience may also be considered.

Experience

• 2 to 5 years of relevant experience in computer vision, artificial intelligence, machine learning, image processing, or industrial automation.
• Freshers with strong computer vision projects, internships, GitHub portfolios, or practical deployment experience may also be considered for a junior position.

Preferred Experience

• Experience in manufacturing, FMCG, packaging, warehouse, logistics, or quality-control environments.
• Experience in defect detection, packaging inspection, bag counting, OCR, vehicle monitoring, or industrial surveillance.
• Experience working with production-line cameras and real-time video streams.
• Knowledge of PLC, IoT devices, sensors, and industrial automation systems.
• Familiarity with cloud platforms such as AWS, Azure, or Google Cloud.
• Experience in dashboard integration using Power BI, Grafana, Streamlit, or web applications.

Behavioural Competencies

• Strong analytical and problem-solving ability.
• Ability to work independently at factory and project locations.
• Good communication and documentation skills.
• Willingness to test solutions in real production environments.
• Ability to coordinate with technical and non-technical stakeholders.
• Strong attention to detail and commitment to accuracy.
• Ability to manage multiple projects and priorities.
• Willingness to learn new technologies and continuously improve deployed solutions.

Key Performance Indicators

• Accuracy and reliability of deployed computer vision models.
• Reduction in false detections and missed detections.
• System uptime and response time.
• Successful completion of projects within the approved timeline.
• Improvement in process automation and reduction in manual effort.
• Speed of issue resolution and production support.
• Quality of technical documentation and user training.
• Successful integration with existing databases, servers, reports, and business systems.

Key Projects Under the Role

• OCR-based bag and packaging identification.
• Product and packaging defect detection.
• Automated bag, carton, pallet, or vehicle counting.
• Container entry, loading, and inspection monitoring.
• Label, barcode, QR code, and batch-number verification.
• Production-line compliance monitoring.
• Safety-equipment and restricted-area monitoring.
• Automated image-based quality inspection.
• Real-time camera dashboards and exception alerts.
• Integration of computer vision outputs with ERP, databases, and reporting systems.

Those who are interested can share resume at Indrila.das@jaytea.com with Current CTC, Expected CTC and Notice Period.