Computer Vision Engineer specializing in production-ready vision systems with
proven business impact.
Core Expertise:
šÆ Object Detection & Segmentation: YOLO8, medical imaging, custom architectures
šÆ Document AI & OCR: 98%+ precision on vehicle documents using Tesseract + OpenCV
šÆ Video Analytics: Built rPPG system for remote heart rate estimation (16 BPM MAE)
šÆ Image Processing: Advanced preprocessing, augmentation, feature engineering
Production-Grade Skills:
ā
MLOps: Docker, CI/CD, model versioning (MLflow, DVC)
ā
Cloud Deployment: AWS (Lambda, S3, Textract, SageMaker)
ā
Scalable APIs: FastAPI for real-time inference
ā
Full Pipeline: Data collection ā training ā deployment ā monitoring
Real Impact:
ā 87% reduction in document processing time
ā 95%+ accuracy on classification tasks
ā Serverless architectures handling production traffic
Tech: Python ā¢ TensorFlow ā¢ PyTorch ā¢ OpenCV ā¢ AWS ā¢ Docker
Looking for: CV Engineering roles where I can push boundaries of what's possible
with vision AI.More...