Linguist III — NLP Data & Prompt Engineer

PRI Global; Redmond (WA); On-site; USD 110,000 - 160,000; Full time

Job summary

PRI Global is seeking a Linguist III in Redmond, WA to develop language components for voice-enabled technologies. The role focuses on linguistic data analysis, language technologies, LLM-powered data synthesis, annotation, prompt engineering, rule-based classifier development, and quality evaluation.

You will collaborate with linguists and data teams on data collection, curation, and annotation, evaluate datasets for ML models, and support prompt engineering for LLM applications.

Qualifications

• Bachelor's degree in Linguistics, Computational Linguistics, or related field.
• 4–5+ years of relevant experience.
• Proficiency with Python.
• Experience with SQL/database queries, spreadsheets, and data analysis.
• Experience with regular expression (regex) encoding.
• Knowledge of syntax, semantics, pragmatics, sociolinguistics, corpus linguistics.
• Experience working with speech and text data.
• Familiarity with LLMs, prompt engineering, and their applications.
• Strong organizational, analytical, communication, and collaboration skills.

Responsibilities

• Collaborate with linguists and data operations teams on data collection, curation, and annotation.
• Evaluate and curate datasets for ML models using LLM-based solutions.
• Assess model performance and data quality.
• Perform prompt engineering and support LLM applications.
• Develop guidelines to ensure consistent, high-quality language-data labeling.
• Create and maintain complex, consistent linguistic analyses.
• Work with speech and text data in a fast-paced, collaborative environment.

Skills

Python

SQL

Regex

Data analysis

Linguistics

Prompt engineering

Data annotation

Collaboration

LLMs

Education

Bachelor's degree in Linguistics, Computational Linguistics, or related field

Tools

NLP libraries

ML frameworks

Job description

PRI Global is seeking a Linguist III in Redmond, WA to develop language components for voice-enabled technologies. The role focuses on linguistic data analysis, language technologies, LLM-powered data synthesis, annotation, prompt engineering, rule-based classifier development, and quality evaluation.

You will collaborate with linguists and data teams on data collection, curation, and annotation, evaluate datasets for ML models, and support prompt engineering for LLM applications.