Data Scientist

We are looking for a highly skilled Data Scientist with expertise in document analysis, leveraging LLMs (Large Language Models) and rule-based algorithms to extract, process, and analyze structured and unstructured data. You will work on cutting-edge solutions involving Azure Document Intelligence, Retrieval-Augmented Generation (RAG), and Knowledge Graphs, helping to drive innovation in document automation.

Key Responsibilities

• Develop and optimize document analysis applications using LLMs and rule-based techniques.
• Process and extract data from PDF, Excel, and Word files.
• Implement RAG pipelines to enhance retrieval and reasoning capabilities.
• Utilize Azure Document Intelligence for document automation.
• Design and maintain Knowledge Graphs for structured data representation.
• Build and optimize REST APIs for document processing applications.
• Ensure strong coding practices and scalable software development in Python.
• Work with SQL databases to store and manage extracted information.
• Collaborate with cross-functional teams and communicate findings effectively.

Core Skills & Qualifications

• Python (strong programming experience)
• SQL & general database knowledge
• Experience handling PDF, Excel, and Word files
• Familiarity with LLM APIs (OpenAI, etc.)
• Expertise in Azure Document Intelligence
• Retrieval-Augmented Generation (RAG)
• Knowledge Graphs for structured data modeling
• Experience with REST APIs & software development
• Strong analytical and communication skills

Nice-to-Have Skills

• Databricks experience
• Understanding of insurance and cyber topics