Applied AI/ML Lead

What you'll do

• Lead the design, development, and production deployment of AI/ML solutions for image classification and text categorization.
• Architect and implement computer vision pipelines using CRNN architectures for document identification and feature extraction.
• Develop and fine-tune models for named entity recognition and semantic understanding to extract structured data from complex documents.
• Integrate OCR technology and generative AI capabilities via Amazon Bedrock into the document processing pipeline.
• Build scalable ML training and inference pipelines using AWS SageMaker for real-time and batch processing.
• Establish MLOps practices including model versioning, automated retraining, drift detection, and performance monitoring.
• Design and manage labeling strategies to ensure high-quality ground truth datasets for training.
• Maintain high-performance data pipelines to process large volumes of scanned document images across enterprise workflows.

What we're looking for

• Bachelor’s degree, MS, or PhD in a quantitative discipline such as Computer Science, Mathematics, Operations Research, or Data Science.
• 7+ years of experience in applied ML/AI roles with at least 2+ years leading teams or large-scale ML initiatives.
• Advanced proficiency in Python and enterprise languages, including Java or Groovy for backend integration.
• Deep expertise in computer vision and NLP models, specifically CRNN architectures and transformer-based models for text categorization and NER.
• Practical experience with OCR technologies and image preprocessing for scanned TIF documents.
• Hands-on experience with AWS SageMaker, Amazon Bedrock, and deploying containerized microservices on AWS EKS using Docker and Kubernetes.
• Strong knowledge of MLOps tools and practices such as MLflow or SageMaker Pipelines for experiment tracking and lifecycle management.
• Domain expertise in the healthcare industry (preferred); experience in document processing, computer vision, or NLP domains (preferred).