Croatian Data Analyst Contractor for Multilingual NLP

Lightcast; Abbeyville (CO); On-site; USD 55,000 - 83,000; Full time

Job summary

Lightcast seeks a Data Analyst (Croatian) to support multilingual data quality across global initiatives. You will work with Linguistics and Engineering teams to build parsers, evaluate text classifiers, and translate taxonomies for global markets.

This is a full-time independent contractor role for up to 6 months, requiring your own laptop and reliable internet. Responsibilities include data quality improvement, cross-language parser development, taxonomy translation, and data cleaning using

Qualifications

• Proficiency in reading and writing Croatian
• Multilingual candidates preferred (Bosnian/Serbian)
• Bachelor's degree in Linguistics, Data Analytics, NLP or related field preferred
• Experience with Microsoft Excel (VLOOKUP, data cleanup, functions)
• Knowledge of query languages such as SQL
• Advanced knowledge of RegEx
• Knowledge of text analysis or ML principles
• Data analysis experience with Excel

Responsibilities

• Analyze and improve the data quality of multilingual text classifiers
• Partner with Linguistics and Engineering teams to develop parsers across multiple languages
• Translate taxonomies including Skills, Titles, and Occupations
• Analyze and clean data using Excel and other data analysis tools
• Apply language, data, and text analysis expertise to support high-quality global data

Skills

Croatian language proficiency

SQL

RegEx

Excel

Multilingual

Independent worker

Education

Bachelor's degree in Linguistics/Data Analytics/NLP

Tools

Microsoft Excel

SQL

Job description

Lightcast seeks a Data Analyst (Croatian) to support multilingual data quality across global initiatives. You will work with Linguistics and Engineering teams to build parsers, evaluate text classifiers, and translate taxonomies for global markets.

This is a full-time independent contractor role for up to 6 months, requiring your own laptop and reliable internet. Responsibilities include data quality improvement, cross-language parser development, taxonomy translation, and data cleaning using