Data Scientist

Data Scientist / Data Engineer – AI/LLM & Metadata Harmonization

Spring House, PA (Hybrid – 3 days/week onsite)

As the Data Scientist / Data Engineer, you will work across business and technology teams at a Fortune 50 Life Sciences company to support metadata harmonization and AI/LLM-driven initiatives across its data science organization. This role blends data engineering, data curation, and applied AI work, and offers the opportunity to build automated pipelines and explore emerging LLM tooling as part of a high-visibility, cross-functional data integration effort.

MINIMUM QUALIFICATIONS

• Master's or PhD in Data Science, Computer Science, or a related field
• Strong Python scripting skills, with prior experience building ETL pipelines
• Proficiency in Python and SQL for designing and developing automated ETL pipelines
• Experience with Information Retrieval, Search technologies, and NLP
• Hands-on experience with AI/LLM frameworks such as the OpenAI API, LangChain, and GPT models
• Prompt engineering experience

RESPONSIBILITIES

• Design and develop automated ETL pipelines to extract, transform, and harmonize metadata across the data science team
• Define and maintain metadata standards and formatting conventions used across the broader team
• Map and reconcile data across multiple resource types, each containing different data structures, into a consistent format
• Build automation to match and validate large sets of fields across data sources
• Support a second initiative applying AI tools and prompt engineering to surface and understand initiatives from internal and public data sources, including BI data points and API-pulled data
• Transform raw internal and public data into standardized, usable formats
• Balance technical build work with data curation responsibilities across two concurrent projects