Data Analyst – Taxonomy and Classification

About the role

Lightcast is seeking a Data Analyst focused on taxonomy and classification to enhance the quality, coverage, and relevance of its labor‑market data products. You will work with large‑scale natural language datasets, resolve ambiguities, and support the evolution of our enriched data models.

Key responsibilities

• Interpret and classify job titles, postings, and company names using NLP techniques.
• Perform root‑cause analysis to identify and fix data quality and classification issues.
• Develop and maintain decision‑making criteria, enrichment processes, and quality‑assurance standards.
• Conduct research to improve taxonomies and uncover new use‑case opportunities.
• Execute data extraction, ETL, and mining using SQL, Python, R, Excel, and related tools.
• Work with relational databases such as Snowflake, PostgreSQL, SQL Server, or SQLite.
• Communicate findings and taxonomy issues to technical teams and stakeholders.
• Respond to customer feedback regarding dataset and taxonomy accuracy.
• Support product road‑mapping, project scoping, and process improvements.
• Utilize visualization and project‑management tools like Kibana, Looker, Tableau, Jira, Wrike, or Asana.

Required profile

• Bachelor’s degree in Data Analytics, Information Systems, Computer Science, Mathematics or a related field (advanced degree preferred).
• 1–3 years of experience with machine‑learning classification models, taxonomy development, or maintaining proprietary/government taxonomies.
• Experience with SQL and query languages such as Elasticsearch, KQL, or SPARQL.
• Understanding of text analysis, NLP, machine learning, and statistical techniques.
• Familiarity with AI coding copilots (e.g., Claude, Codex) is a plus.

Required skills

• Python, R, Excel
• SQL, Snowflake, PostgreSQL, SQL Server, SQLite
• Elasticsearch, KQL, SPARQL
• NLP and text‑analysis libraries
• Data extraction, ETL, data mining
• Kibana, Looker, Tableau
• Jira, Wrike, Asana