Data Scientist R2

Job Responsibilities

• Materials Solutions Platform Development & Strategic Impact- Collaborate with Materials SME, platform architects and product managers to define data-driven features for Materials (e.g. polymer selection, formulation prediction, and performance benchmarking) across multiple application segments.
• Data Extraction and Pipeline Development- Design and manage data extraction pipelines for materials-related documents (TDS, patents, publications) using Python, spaCy, ChemDataExtractor, OCR tools.
• Build automated workflows for data cleaning, annotation, tagging, and mapping using pandas, NumPy, regex, Snakemake.
• Semantic Modeling & Knowledge Graphs- Create structured databases and semantic knowledge graphs linking structure, properties, and applications using Neo4j, GraphDB, RDF, OWL.
• Support ontology development in collaboration with domain scientists (e.g., polymer thesaurus, CAS Lexicon) using Protg, OWL, XML.
• AI/ML Dataset Preparation- Deliver validated, AI-ready datasets for property prediction, formulation optimization, material recommendation, or performance analysis using scikit-learn, TensorFlow, PyTorch.
• Collaborate with software, NLP, and product teams to integrate polymer data into customer-facing tools or internal dashboards.
• Data Quality & Interoperability- Ensure data accuracy, consistency, and interoperability across all informatics workflows.
• Document pipelines and models using Jupyter Notebooks and maintain reproducibility standards with version control (GitHub). Ideal Candidate will have
• A data-oriented technologist with a passion for organizing and structuring scientific knowledge.
• Solid foundation in data science or informatics, combined with a working understanding of structure-property-application relationships in materials/polymers.
• Prior experience working with scientific or technical data from TDS, patents, or journals.
• Skills in building pipelines, semantic models, and knowledge graphs for complex scientific data domains.
• Mindset that values data Values clean data, reproducibility, and cross-disciplinary collaboration.
  

Job Requirements

• B.Tech / M.Tech / Ph.D. in Data Science, Computer Science, Chemical Informatics, or Materials Informatics.
• 26 years of experience in informatics/data science roles with exposure to scientific/engineering domains.
• Proficiency in Python, SQL, and data science libraries (pandas, spaCy, scikit-learn).
• Experience with semantic modeling, graph databases (e.g., Neo4j, GraphDB), and knowledge representation standards (RDF, OWL).
• Exposure to polymer/materials datasets and platforms like PoLyInfo, CAS SciFinder, MatWeb (preferred).
• Familiarity with cheminformatics tools (RDKit, ChemAxon) and NLP pipelines for scientific text mining