Computer Vision Engineer (Object Detection & Model Deployment)
We are looking for a Computer Vision Engineer who will take full ownership of our object detection pipeline — covering data collection, preprocessing, training, evaluation, and deployment. The ideal candidate has strong knowledge of CNN architectures, YOLO models, and experience automating ML workflows.
Responsibilities
• Lead the full lifecycle of object detection model development (data gathering → preprocessing → training → evaluation → deployment)
• Build and maintain scalable datasets for object detection tasks
• Develop, train, and optimize CNN and YOLO-based models for accuracy and performance
• Automate the model training pipeline to retrain models as new data arrives
• Deploy models to production with a focus on robustness, speed, and monitoring
• Perform ongoing model evaluation, error analysis, and improvements
• Collaborate with engineering teams to integrate models into real-world systems
Requirements
• Strong understanding of computer vision, image processing, and deep learning
• Experience with CNN architectures and YOLO (v8/v9/v11 or similar)
• Hands-on experience in training, fine-tuning, and optimizing object detection models
• Experience building automated ML pipelines (Python, Bash, scheduling, CI/CD)
• Proficiency with PyTorch or TensorFlow
• Familiarity with data lifecycle management (annotation, augmentation, versioning)
• Ability to deploy models using Docker, REST APIs, or edge devices
• Strong problem-solving skills and ownership mentality