Machine Learning Engineer | AI /ML Engineer

AI/ML Solution Development: Design, build, and deploy production-grade AI/ML models and pipelines addressing business needs such as object detection, container/vehicle recognition, OCR extraction, anomaly detection, predictive analytics, and operational automation.

• Computer Vision Engineering: Develop CV models using CNNs, EfficientDet, YOLO, RCNN variations, segmentation models, and multi-view camera pipelines tailored for container terminal operations, crane OCR systems, and security applications.
• LIDAR & Sensor Data Processing: Work with LIDAR point clouds, depth maps, and 3D object detection frameworks to build perception systems for equipment monitoring, spatial analysis, and automated safety workflows.
• OCR Engineering: Implement OCR and document understanding workflows using Tesseract, EasyOCR, PaddleOCR, Azure Cognitive Services, or custom deep learning-based OCR architectures.
• Model Training & Optimization: Perform dataset preparation, augmentation, labeling, hyperparameter tuning, and model optimization for latency, accuracy, and real-time inference.
• MLOps & Production Deployment: Build scalable CI/CD and MLOps pipelines using Azure Machine Learning, Kubernetes, Docker, MLflow, or similar frameworks for model versioning, monitoring, and retraining.
• Data Engineering Collaboration: Work closely with data engineering teams to build robust data pipelines, feature stores, and ETL/ELT processes supporting AI/ML use cases.
• Integration with Microservices: Package AI/ML models as microservices or Minimal API-based inference endpoints for integration into enterprise applications.
• Research & Innovation: Explore and evaluate emerging AI, CV, LIDAR, and OCR technologies, producing PoCs and technical documentation with pros/cons and recommendations.
• Cross-functional Collaboration: Work closely with Technical Architects, Software Engineers, QA, and Product Managers to ensure AI/ML solutions fit seamlessly into the architecture and meet business objectives.
• Performance Monitoring: Implement monitoring, logging, drift detection, and performance evaluation for models running in production.
• Documentation & Knowledge Sharing: Produce clear technical documentation, architecture diagrams, model cards, and best practices; mentor juniors in AI/ML concepts