3 days ago
Hyderābād, IndiaSenior
Responsibilities
- Design, build, maintain, govern, and document CMC ontologies, controlled vocabularies, semantic mappings, and knowledge graph representations.
- Map CMC workflows and build automated pipelines to extract stability protocols, reports, and results from varied CDMO-generated PDFs and other sources.
- Standardize extracted data into auditable, ontology-aligned structures and validate extraction accuracy against historical Excel data and linked PDFs.
- Enable stability analytics such as trending, shelf-life estimation, out-of-trend and out-of-specification signaling, alerting, and regulatory reporting.
- Extend data catalog and data lake capabilities for reusable CMC use cases across stability, manufacturing, specifications, reference standards, and document management.
- Implement GxP-aligned governance, access control, traceability, data lineage, audit trails, ontology versioning, and change control.
- Collaborate with CMC subject matter experts, data architecture leads, IT, statisticians, and stability scientists to deliver a proof of concept and scalable solution.
- Evaluate build-versus-buy-versus-integrate options for stability management, LIMS, and semantic platform tooling.
Requirements
- Bachelor’s degree in Computer Science, Data Engineering, Information Science, Life Sciences Informatics, Chemistry, or a related field; a master’s degree is preferred.
- At least 5 years of experience in data engineering, knowledge engineering, or scientific informatics, including data pipelines, ETL/ELT processes, or document and data extraction solutions.
- Hands-on experience designing ontologies, taxonomies, or semantic data models and working with relational, document, or graph databases.
- Understanding of pharmaceutical stability programs, including protocols, storage conditions, pull points, test methods, specifications, OOT/OOS, and the ICH Q1 guideline family.
- Hands-on experience with PDF and document parsing, OCR, layout-aware extraction, and table extraction from unstructured or semi-structured documents.
- Familiarity with regulated GxP data environments, ALCOA+ data integrity, audit trails, traceability, and access control.
- Proficiency in Python or a similar language and SQL; familiarity with SPARQL and optionally Cypher.
- Strong communication skills and the ability to translate between CMC scientists and technical teams in a cross-functional, evolving environment.
- Preferred qualifications include pharma or biotech CMC experience, Allotrope and Pistoia Alliance ontology familiarity, FAIR data principles, graph platforms, stability systems or LIMS, Benchling, SharePoint, JMP, Spotfire, stability statistics, AI-assisted extraction, CDMO collaboration, CTD/eCTD structures, CSV/CSA, and proof-of-concept delivery.
Benefits
- Hybrid work arrangement in Hyderabad or Bangalore.