Senior UX Language Researcher - Variable Staffing Pool

Humana
Full-time•$104k-143k/year (USD)

📍 Job Overview

Job Title: Senior UX Language Researcher - Variable Staffing Pool

Company: Humana

Location: Remote US

Job Type: Part time

Category: User Experience (UX) Research / Data Science

Date Posted: July 31, 2026

Experience Level: 5-10 years

Remote Status: Remote

🚀 Role Summary

  • This role involves deep analysis of conversational data, focusing on evaluating Large Language Model (LLM) performance through metrics such as accuracy, fallback rate, and hallucination rate, crucial for optimizing user experience in healthcare technology.

  • The position requires strong computational linguistics and language data processing skills to manage and analyze transcription and annotation projects, ensuring high-quality datasets for AI model development and refinement.

  • Candidates will contribute to process improvements and software enhancements, demonstrating autonomy and a proactive approach to problem-solving within a fast-paced, data-driven environment.

  • A significant aspect of the role is cross-functional collaboration, providing data quality expertise and advocating for best practices in language data labeling to UX, Product, and Engineering teams.

📝 Enhancement Note: This role is categorized under UX Research and Data Science due to its focus on analyzing user interaction data (conversational transcripts) to improve digital products and services. The emphasis on LLMs and computational linguistics points towards a specialized data science function within UX. The "Variable Staffing Pool" designation indicates a need for flexible, potentially part-time work based on business demand, which is a key differentiator for operations and project-based roles.

📈 Primary Responsibilities

  • Analyze conversational transcripts and chat data to derive industry-standard metrics such as accuracy, fallback rate, and hallucination rate for LLM performance evaluation.

  • Manage and oversee transcription and annotation projects, specifically for LLM-based metrics, ensuring adherence to quality standards and project timelines.

  • Conduct in-depth qualitative error trend analysis on conversational data, identifying patterns and developing actionable plans to enhance

Application Requirements

Candidates must have at least 5 years of related experience, including 2 years in computational linguistics or language data processing. A bachelor's degree is required, along with proficiency in Python, R, SQL, and data annotation best practices.