Sr. Data Scientist

Description Join a federal wildlife conservation modernization initiative focused on transforming decades of permits, certificates, inspection records, and wildlife trade documentation into structured, searchable data assets.

As a Senior Data Scientist, you will design and implement Document AI, OCR, machine learning, and natural language processing solutions that convert complex, unstructured records into valuable data used to support conservation, compliance, analytics, and regulatory decision-making.

This role offers the opportunity to work on a high-impact modernization effort while building scalable AI-powered document intelligence capabilities in a cloud-based environment.

What You'll DoDesign and develop OCR and Document AI solutions for large collections of scanned records, permits, certificates, and legacy documents

Build machine learning and NLP models that extract, classify, validate, and transform unstructured information into structured data Create document understanding workflows that support information extraction, taxonomy-based classification, and entity identification

Develop confidence scoring frameworks and exception-handling workflows for low-confidence outputs

Support human-in-the-loop review processes that improve data quality and model performance

Evaluate model performance using precision, recall, error analysis, and other machine learning metrics

Build reproducible and auditable machine learning pipelines with clear lineage and validation practices

Develop solutions that support reconciliation and relationship mapping across permits, applicants, species, countries, shipments, and related records

Collaborate closely with data architects, subject matter experts, business analysts, and platform engineers

Support cloud-based AI and data processing solutions using AWS services and modern machine learning frameworks

Required Qualifications Experience developing and deploying machine learning solutions in production environments

Strong Natural Language Processing (NLP) experience

Advanced Python development skills

Strong SQL and PostgreSQL experience

Experience building data science solutions in AWS cloud environments

Experience working with OCR, Document AI, Intelligent Document Processing (IDP), or document understanding technologies

Experience with predictive modeling, classification, information extraction, or related machine learning techniques

Experience evaluating model performance and improving accuracy through iterative testing and analysis

Ability to obtain a U.S. Government Position of Public Trust

Preferred Qualifications AWS TextractAWS Bedrock AWS SageMakerAWS Lambda Document Intelligence platforms

Intelligent Document Processing (IDP)
Entity extraction and record reconciliation

Layout-aware document models

Experience operating within government, highly regulated, or compliance-focused environments

Experience building human-in-the-loop AI workflows

Technologies You'll UsePythonSQL / PostgreSQL AWS Cloud Services AWS TextractAWS Bedrock AWS SageMakerAWS Lambda Machine Learning Natural Language ProcessingOCRDocument AI Intelligent Document Processing Predictive Analytics Team & Environment You'll work alongside data architects, platform engineers, business analysts, and domain subject matter experts supporting a mission-driven federal modernization initiative. The program is focused on improving accessibility, traceability, analytics, and reporting across critical wildlife trade data systems through the use of modern AI and machine learning technologies.

Additional

Skills & Qualifications Must be able to pass a government background check and be in a Position of Public Trust.

Experience Level Intermediate Level Job Type & Location This is a Contract position based out of Fort…