Data Scientist Lead

About the Role

As Data Scientist Lead within the Commercial & Investment Bank's Healthcare Provider team, you will lead a team in building advanced solutions for image classification, text categorization, and intelligent data extraction from scanned documents. This role involves managing the full ML lifecycle, from prototyping to production deployment on AWS EKS.

Responsibilities

• Lead and mentor a team of data scientists in designing and executing advanced analytics and modeling projects focused on image classification, text categorization, and intelligent data extraction from scanned document images.
• Foster a culture of curiosity, analytical rigor, and continuous learning by developing team members in deep learning, computer vision, NLP, and document AI techniques.
• Define and drive the analytical strategy for document understanding use cases, identifying the optimal combination of computer vision, NLP, and multimodal approaches.
• Build and fine-tune multimodal document understanding and text categorization models, leveraging textual content, spatial layout, and visual features for structured data extraction.
• Design rigorous experimentation and data quality frameworks, including A/B testing, cross-validation, and statistical significance testing.
• Establish best practices for annotation quality management, training data curation, active learning, and ground truth validation.
• Develop and deploy models using Python and AWS SageMaker, managing the full lifecycle from exploratory data analysis to production deployment and monitoring.
• Collaborate with data engineers and ML engineers to integrate models into production document processing pipelines.

Requirements

• Bachelor's degree or higher in a quantitative discipline (Computer Science, Mathematics, Operations Research, Data Science, etc.).
• 7+ years of experience in data science or quantitative analytics, with 2+ years in document AI, computer vision, or NLP.
• Strong foundation in statistics, mathematics, and programming, including probability, modeling, and experimental design.
• Advanced proficiency in Python, PyTorch, TensorFlow, Hugging Face Transformers, scikit-learn, OpenCV, pandas, NumPy, matplotlib, and seaborn.
• Hands-on experience with CNNs, transformer architectures, OCR technologies, and multimodal document understanding models.
• Proficiency in AWS SageMaker, Amazon Bedrock, and containerized deployments on AWS EKS.
• Experience with SQL, Oracle databases, Java, Groovy, and annotation tools for supervised learning.

Qualifications

• Deep expertise in image preprocessing techniques for scanned documents (deskewing, binarization, noise removal, etc.).
• Familiarity with NLP models for text categorization, sequence labeling, named entity recognition, and semantic analysis.
• Understanding of OCR accuracy metrics, preprocessing optimization, and error analysis.

Skills

• Strong leadership and mentoring abilities.
• Ability to drive analytical strategy and innovation.
• Proficiency in designing and implementing rigorous experimentation frameworks.
• Experience with cloud-based ML model deployment and monitoring.

Preferred Qualifications

• Domain expertise in the healthcare industry.

About Us
JPMorgan Chase, a 200-year-old financial institution, offers innovative solutions to consumers, businesses, and governments globally under the J.P. Morgan and Chase brands. We lead in investment banking, consumer banking, commercial banking, financial transaction processing, and asset management. Our competitive total rewards package includes base salary, performance-based incentives, and comprehensive benefits like health care, retirement plans, and professional development support.

About the Team
J.P. Morgan's Commercial & Investment Bank is a global leader in banking, markets, securities services, and payments, serving clients in over 100 countries. The team provides strategic advice, capital raising, risk management, and liquidity solutions to corporations, governments, and institutions worldwide.