Data Analyst

Location: Chicago/Atlanta/NYC/NJ/ Cleveland, OH

Job Title: Data Analyst

Mode of work: Hybrid 3 days a week must

Experience: 10+ years

Primary skills: Python, Gen AI

Good to have Insurance domain- P&C

Job Description:

• Who has experience preparing datasets for LLM-based applications, Retrieval-Augmented Generation (RAG) or chatbot systems.
• Who is comfortable working with structured and semi-structured insurance data to build curated knowledge inputs.
• Who can annotate fields, data structures, documents, create prompt-response structures, and support semantic chunking strategies.
• Who can contribute to the development of our semantic model, including defining taxonomies, ontologies, and synonym sets for insurance concepts.
• Who is proficient in SQL (Snowflake preferred) and able to extract and transform content from large data systems.
• Who understands how LLMs retrieve and process contextual information, including embedding logic and metadata tagging.
• Who is familiar with data governance best practices, especially in regulated domains like insurance, banking, or finance.
• Who has completed a quantitative course such as Mathematics, Statistics, or Computer Science/Engineering. (Preferred, not necessary)

Soft Skills:

• Analytical Thinking: Strong ability to identify patterns, gaps, and inconsistencies in large data sets.
• Research Skills: Able to explore domain-specific terminology and translate it into structured knowledge.
• Collaboration: Comfortable working closely with engineering, data, and domain SMEs in a distributed team.