Linguist III: LLM Data & Prompting Specialist

Spectraforce Technologies; Burlingame (CA); On-site; USD 70,000 - 110,000; Full time

Job summary

Spectraforce Technologies is seeking a Linguist III to contribute to language component development for voice-enabled technologies. The role involves managing data collection, LLM-powered data synthesis, data annotation, prompt engineering, and quality evaluations.

The ideal candidate will have strong linguistic data analysis skills, Python proficiency, and familiarity with LLMs, with onsite work in Burlingame, CA or Redmond, WA, for a 6-month engagement.

Qualifications

• Bachelor's degree in Linguistics or related field required.
• Experience with regular expression encoding.
• Knowledge of syntax, semantics, pragmatics, sociolinguistics, corpus linguistics, and other areas of linguistics.
• Proficiency in Python.
• Experience with database queries and data analysis processes (SQL, spreadsheets).
• Experience working with speech and text data.
• Familiar with Large Language Models (LLMs) and prompt engineering.
• Comfortable in a fast-paced, collaborative environment.
• Strong organizational skills and attention to detail.
• Excellent verbal and written communication skills.

Responsibilities

• Provide linguistic expertise while delivering data for large language models.
• Collaborate with other linguists and data operations teams in data collection, data curation, and annotation efforts.
• Evaluate and curate data sets for ML models using LLM solutions.
• Assess model performance and data quality.
• Prompt engineering.
• Create guidelines to enable annotators to consistently label language data at quality.
• Collaboratively develop complex and consistent linguistic analyses.

Skills

Python

SQL

Regular expressions

LLMs prompt engineering

Data analysis

Communication

Organizational skills

Education

Bachelor's degree in Linguistics or related

Master's degree preferred

Tools

NLP libraries

ML frameworks

Job description

Spectraforce Technologies is seeking a Linguist III to contribute to language component development for voice-enabled technologies. The role involves managing data collection, LLM-powered data synthesis, data annotation, prompt engineering, and quality evaluations.

The ideal candidate will have strong linguistic data analysis skills, Python proficiency, and familiarity with LLMs, with onsite work in Burlingame, CA or Redmond, WA, for a 6-month engagement.