Remote Data Scientist II – AI & NLP for Federal Data

WinTrio LLC; Northern (KY); Hybrid; USD 90,000 - 130,000; Full time

Benefits offered by this job

Healthcare coverage (Medical, Dental, 

FSA/HSA

401(k) and retirement plan

Annual bonus & profit sharing

PTO & vacation

EAP

Life and disability insurance

Job summary

WINTrio LLC is seeking a Data Scientist II to apply AI, NLP, and conversational AI to modernize data collection across web, mobile, and voice channels. You will work on large-scale survey instruments and respondent data pipelines, collaborating with architects and UX researchers to ensure data quality and audit readiness.

The ideal candidate has hands-on experience with NY federal survey programs, NLU/NLP model development, and speech-to-text pipelines, and must be eligible for a NACI background

Qualifications

• 2 to 5 years of applied data science, statistics, or NLP/conversational AI development.
• Experience with survey instruments or statistical data collection programs.
• Experience building/tuning NLU models for structured data extraction from unstructured or spoken input.
• Experience with speech-to-text pipelines and conversational AI platforms.
• Experience in federal or regulated data environments with structured deliverables.
• Familiarity with data validation, metadata standards, and QA practices.
• Experience working with COR and Government stakeholders on structured deliverables.
• Must be eligible for a NACI background investigation.

Responsibilities

• Design and validate statistical models for response accuracy across channels.
• Build and tune NLU models to extract data from open-ended responses.
• Support speech-to-text pipeline accuracy tuning and error analysis.
• Develop confidence-scoring and escalation logic for automation routing to live staff.
• Design metadata schemas and automated validation rules for CI/CD workflows.
• Analyze response and transcript data to identify data quality issues and usability gaps.
• Support testing of AI-driven data collection components across functional, performance, and accuracy dimensions.
• Document data models, validation logic, and AI decision workflows for knowledge transfer and audit readiness.
• Collaborate with solutions architects and UX researchers to align data pipeline design with respondent-facing interfaces.

Skills

Python

SQL

R

Statistical modelling

Pandas/NumPy

Tools

Amazon Lex

Amazon Bedrock

Azure AI Language

Google Dialogflow

spaCy

Job description

WINTrio LLC is seeking a Data Scientist II to apply AI, NLP, and conversational AI to modernize data collection across web, mobile, and voice channels. You will work on large-scale survey instruments and respondent data pipelines, collaborating with architects and UX researchers to ensure data quality and audit readiness.

The ideal candidate has hands-on experience with NY federal survey programs, NLU/NLP model development, and speech-to-text pipelines, and must be eligible for a NACI background