Senior Data Scientist — NLP & Fraud Analytics (Remote)

Node.Digital LLC; Herndon (VA); On-site; USD 140,000 - 210,000; Full time

Benefits offered by this job

Medical

Dental

Vision

Basic Life

Health Saving Account

401K matching

Three weeks PTO/Sick

11 Paid Holidays

Pre-Approved Online Training

Job summary

Node.Digital LLC in Herndon, VA offers a remote-work opportunity focused on building NLP and ML pipelines to parse and analyze large text corpora and support fraud investigations within SBA programs.

You will design, implement, and maintain predictive models, collaborate with investigators and engineers, and deliver actionable insights through dashboards and reports. A strong background in Python, NLP, and cloud platforms is required.

Qualifications

• Master's, Ph.D., or doctorate level equivalent in data science, ML, CS, math, or related field, or 10+ years of relevant work experience.
• 5+ years designing, implementing, and maintaining advanced AI systems and predictive models.
• 5+ years developing analytic rules and models using leading analytic tools and best practices.
• 5+ years developing regression, classification, and other statistical models.
• 3+ years providing data support for criminal investigations into financial fraud.
• 3+ years manipulating data in Python; Pandas required.
• 3+ years cloud experience (Azure, AWS, or GCP; certs preferred).
• 2+ years SQL (SQL Server, PostgreSQL).
• 2+ years developing and scaling NLP solutions.
• 2+ years presenting methods to technical and non-technical stakeholders.

Responsibilities

• Integrate and scale NLP methods to parse, clean, and analyze large corpora of unstructured text using OCR and semantic similarity.
• Design and implement ML models targeting financial fraud and improper payments within SBA programs.
• Build supervised and unsupervised models (regression, Bayesian, clustering, ensembles).
• Review, maintain, and support existing loan fraud indicators.
• Collaborate with investigators to determine analytic strategies and follow federal criminal procedure rules.
• Produce case leads from model outcomes and document methodologies for evidentiary purposes.
• Create dashboards and visuals to communicate methodology, outcomes, and predictive capability.
• Coordinate with data engineering to support ML and text-processing pipelines.
• Create automation with SharePoint, Python, Excel, Power BI, Power Apps.
• Identify new business questions for expanded analysis and reporting.

Skills

Python

Pandas

NLP

SQL

Cloud platforms

ML modeling

Data analysis

Education

Master's or PhD in data science / ML / CS / Math

Ten years of related work experience

Tools

SharePoint

Power BI

Power Apps

Excel

SQL Server

PostgreSQL

Job description

Node.Digital LLC in Herndon, VA offers a remote-work opportunity focused on building NLP and ML pipelines to parse and analyze large text corpora and support fraud investigations within SBA programs.

You will design, implement, and maintain predictive models, collaborate with investigators and engineers, and deliver actionable insights through dashboards and reports. A strong background in Python, NLP, and cloud platforms is required.