[Your Full Name]
[Your Phone Number] | [Your Email] | [City, State]
LinkedIn: [Your LinkedIn URL] | GitHub: [Your GitHub URL]

PROFESSIONAL SUMMARY
Computer Vision Data Scientist with [X] years building image and video analysis systems. Expert in CNNs, object detection, and image segmentation with proven ability to achieve [Y%] accuracy. Strong track record deploying CV models processing [X]M images daily in production.

TECHNICAL SKILLS
Computer Vision: Object Detection, Image Segmentation, Image Classification, Pose Estimation, Face Recognition, OCR, 3D Vision
Architectures: ResNet, YOLO, Faster R-CNN, U-Net, EfficientNet, Vision Transformers
Frameworks: PyTorch, TensorFlow, OpenCV, torchvision, Detectron2, MMDetection
Tools: CUDA, TensorRT, ONNX, LabelImg, CVAT
Cloud: AWS (Rekognition, SageMaker), GCP Vision AI, Azure Computer Vision

PROFESSIONAL EXPERIENCE

Computer Vision Engineer / Data Scientist
[Company Name], [City, State]
[Start Date] – Present
• Developed object detection system achieving [X%] mAP on custom dataset with [Y] classes
• Built image segmentation model with [X%] IoU processing [Y]K images per hour
• Deployed real-time inference pipeline handling [X] FPS on [hardware specification]
• Reduced false positive rate from [X%] to [Y%] through model optimization
• Created data annotation pipeline labeling [X]K images with quality control
• Optimized model inference time by [Z]x through quantization and pruning

Computer Vision Engineer
[Previous Company Name], [City, State]
[Start Date] – [End Date]
• Built facial recognition system with [X%] accuracy under various lighting conditions
• Implemented image classification pipeline achieving [Y%] top-1 accuracy
• Developed custom augmentation strategies improving generalization by [Z%]
• Created OCR solution extracting text with [accuracy percentage] on [document types]
• Trained models on [X]M images using distributed training reducing time by [Y%]

TECHNICAL PROJECTS

[Project Name]: Object Detection System
• Task: Detect and localize [objects] in [environment/scenario]
• Architecture: [YOLO v5, Faster R-CNN, etc.] with [modifications]
• Performance: [mAP score] at [FPS] on [hardware]
• Deployment: [Production details and scale]

[Project Name]: Image Segmentation Pipeline
• Challenge: Segment [target objects] in [challenging conditions]
• Approach: [U-Net, Mask R-CNN, etc.] with [custom loss function]
• Results: [IoU/Dice score] on [dataset size]
• Impact: [Business outcome or application]

[Project Name]: Video Analysis System
• Application: [Specific use case like activity recognition, tracking]
• Method: [Technical approach and architecture]
• Performance: [Metrics and real-time capability]

EDUCATION
[Degree Name], [Computer Science, EE, or related]
[University Name], [City, State]
Graduation: [Year]

PUBLICATIONS
• [CV-related paper], [Conference], [Year]

CERTIFICATIONS
• [Computer Vision Specialization], [Year]
• [Deep Learning Certificate], [Year]

TECHNICAL EXPERTISE
• Image Processing: Filtering, edge detection, morphological operations, color spaces
• Data Augmentation: Rotation, scaling, flipping, color jittering, mixup, cutout
• Model Training: Transfer learning, multi-task learning, weakly supervised learning
• Deployment: Model optimization, edge deployment, real-time inference