Data Scientist

• Pharma • Start ASAP/to determinate • 100% remote • B2B up to 50 e/h netto+VAT The role of the Data Scientist in RAG & Document Intelligence focuses on designing and implementing AI solutions that enhance the accessibility of knowledge within an organization, transforming complex enterprise documents into actionable insights. Main Responsibilities: • Optimize RAG pipelines by experimenting with various strategies for parsing, chunking, and retrieval to improve answer quality and reduce errors. • Extract structured information from unstructured content, ensuring high-quality input for processing. • Design and conduct experiments to evaluate models based on accuracy, latency, and cost, and derive insights from the data. • Implement NLP techniques to solve real-world problems, enhancing user experience through effective query handling. • Monitor and evaluate the performance of AI models and make necessary adjustments for cost-efficiency. Key Requirements: • Strong Python skills with experience in machine learning and generative AI workflows. • Solid understanding of NLP principles like text representation and semantic search. • Experience in designing and optimizing RAG pipelines for unstructured documents. • Proficiency with document parsing and handling diverse formats. • Familiarity with evaluation frameworks for LLMs and defining specific quality metrics. • Knowledge of multi-agent AI frameworks. • Experience with vector databases and cloud services (Azure/AWS). • Strong analytical skills with an experimental approach to problem solving. • Fluent in English (written and spoken). Nice to Have: • Hands-on experience with Databricks GenAI products. • API development and integration skills. • Familiarity with Model Context Protocol. • Knowledge of knowledge management and taxonomy design. Other Details: • Impact Level: Greenfield AI Initiative • Collaboration: Work with various business units across the organization.