Lead Data Scientist - Document AI & Multimodal ML

JPMorganChase; Tampa (FL); On-site; USD 140,000 - 190,000; Full time

Job summary

JPMorganChase is seeking a Data Scientist Lead to guide a team focused on image classification, text categorization, and intelligent data extraction from scanned documents. You will drive multimodal models, CV/NLP techniques, and production deployments on AWS, shaping analytics strategy across healthcare provider workflows.

The ideal candidate will have 7+ years in data science with hands-on experience in PyTorch, TensorFlow, and AWS SageMaker, plus strong SQL and software engineering

Qualifications

• 7+ years in data science or quantitative analytics.
• 2+ years in document AI, computer vision, or NLP.
• Proficiency in Python for data analysis, modeling, and visualization.
• Hands-on experience with CNN and transformer architectures for document AI.
• Experience deploying ML models on cloud platforms like AWS SageMaker/Bedrock.

Responsibilities

• Lead and mentor a data science team on analytics and ML projects for document understanding.
• Define analytical strategy for document understanding using CV, NLP, and multimodal approaches.
• Build and fine-tune multimodal models extracting structured data from scanned documents.
• Design experiments and data quality frameworks, including A/B testing and validation.
• Develop and deploy models in production, collaborating with data and ML engineers.

Skills

Python

PyTorch

TensorFlow

Hugging Face

AWS SageMaker

OCR

CNN

Transformers

NLP

SQL

Java

Groovy

Education

Bachelor's degree or MS or PhD in quantitative discipline

Tools

AWS Bedrock

EKS

OpenCV

scikit-learn

Pandas

NumPy

Job description

JPMorganChase is seeking a Data Scientist Lead to guide a team focused on image classification, text categorization, and intelligent data extraction from scanned documents. You will drive multimodal models, CV/NLP techniques, and production deployments on AWS, shaping analytics strategy across healthcare provider workflows.

The ideal candidate will have 7+ years in data science with hands-on experience in PyTorch, TensorFlow, and AWS SageMaker, plus strong SQL and software engineering