Computer Vision Engineer

- 5+ years hands-on computer vision experience

- Deep knowledge and experience with large scale video analytics/stream processing and AI/ML infrastructure

- Deep expertise in object detection frameworks (YOLO, R-CNN, DETR)

- Production experience with PyTorch/TensorFlow for image classification OCR systems experience (Tesseract, PaddleOCR, or custom models)

- Large-scale distributed image processing (billions of images)

- Modern ML techniques: transformers, self-supervised learning, model distillation Docker, distributed training, model deployment at scale

- OpenCV, PIL, albumentations for image preprocessing

- Synthetic data generation