Computer Vision Engineer
Role Overview
Develop and deploy computer vision solutions using deep learning, image processing, and modern CV frameworks. Build production-ready systems for visual understanding and analysis.
Responsibilities
- Design and implement computer vision models for object detection, segmentation, and classification
- Develop image processing pipelines for enhancement, filtering, and feature extraction
- Build and optimize CNN architectures for various computer vision tasks
- Implement CV solutions using OpenCV for real-time image and video processing
- Train and fine-tune deep learning models using PyTorch for production deployment
- Optimize models for performance, accuracy, and inference speed
- Collaborate with cross-functional teams to integrate CV solutions into products
Requirements
- Bachelor's degree in Computer Science, Electrical Engineering, AI/ML, or related field
- Strong expertise in image processing techniques and algorithms
- Proven experience with CNNs and deep learning architectures (ResNet, YOLO, U-Net, etc.)
- Proficiency in OpenCV for computer vision applications
- Hands-on experience with PyTorch for model development and training
- Strong Python programming skills
- Understanding of computer vision fundamentals (feature detection, image transforms, edge detection)
Preferred
- Experience with object detection frameworks (YOLO, Faster R-CNN, SSD)
- Knowledge of semantic/instance segmentation techniques
- Familiarity with vision transformers (ViT, DETR, SAM)
- Experience with video processing and tracking algorithms
- Understanding of 3D vision, depth estimation, or SLAM
- Knowledge of model optimization (TensorRT, ONNX, quantization)
- Experience with GPU programming and CUDA
- Familiarity with cloud deployment and MLOps