CMC Data/Solutions Engineer

Location : Hybrid (Hyderabad/Bangalore) Experience : 6-8 Years Role Summary The CMC Solutions Engineer will design and build the semantic and technical foundation for CMC data, with focus on two areas: developing the CMC ontology and knowledge model, and engineering automated, GxP-relevant stability data workflows. Starting with stability monitoring data from CDMO-generated protocols and reports, this role will move CMC data away from siloed, manual processes (SharePoint, email, manual transcription into Excel) toward a structured, ontology-driven, auditable data layer that supports trending, alerting, regulatory reporting, and AI-assisted analysis. The engineer will work closely with CMC subject matter experts (analytical development, stability, quality, and regulatory CMC), data architecture leads, and existing data catalog/data lake teams to deliver a proof of concept using CDMO data, then iterate toward a scalable, enterprise-reusable solution that extends beyond stability to manufacturing, specifications, reference standards, and document management. Key Responsibilities Ontology & Knowledge Modeling

• Design, build, and maintain the CMC ontology, beginning with the stability domain (studies, protocols, storage conditions, pull points, lots/batches, tests, methods, specifications, results, and impurities) and extending to manufacturing, reference standards, and document management
• Translate CMC business concepts and SME knowledge into well-formed ontologies, controlled vocabulary
• Align and explore applicability of established industry models where appropriate, such as the Allotrope Foundation Ontologies (AFO), Pistoia Alliance IDMP-O, and terminology consistent with ICH Q1 (stability) and ICH Q6 (specifications), rather than building from scratch
• Map extracted and source-system data to ontology classes and properties, and maintain semantic mappings between CDMO-specific terminology and internal standards
• Build and query knowledge graph representations of CMC data to enable cross-study, cross-lot, and cross-CDMO analysis
• Establish ontology governance: versioning, change control, stewardship roles, and documentation that supports use in a regulated environment Stability Workflows & Data Engineering
• Map current-state and design future-state stability workflows end to end, from protocol setup and pull schedules through testing, results review, trending, out-of-trend (OOT) / out-of-specification (OOS) signaling, and reporting for regulatory submissions (e.g., CTD Module 3.2.P.8 / 3.2.S.7)
• Design and build automated pipelines to ingest stability protocols, reports, and results from CDMO-generated PDFs and other sources
• Develop parsing/extraction logic that handles varied PDF formats across CDMOs, including high-volume, structurally complex data
• Standardize extracted data into an ontology-aligned, auditable structure, and use historical Excel data and linked PDFs as a validation set to measure and improve extraction accuracy
• Enable downstream stability analytics, including trending, shelf-life estimation, and alerting (e.g., in JMP and Spotfire), in partnership with statisticians and stability scientists
• Extend existing data catalog/data lake capabilities to support CMC use cases, ensuring the solution is reusable across the broader enterprise Governance, Collaboration & Delivery
• Build in governance, access control, traceability, data lineage, and audit trails consistent with GxP and data integrity (ALCOA+) expectations
• Lay the groundwork for natural-language querying and AI-assisted analysis of CMC data, using the ontology and knowledge graph to ground results
• Collaborate with CMC subject matter experts, data architecture leads, and IT to deliver an initial proof of concept within an agile, discovery-driven scope
• Contribute to build-vs-buy-vs-integrate evaluations for stability management, LIMS, and semantic platform tooling
• Document assumptions, data lineage, ontology design decisions, and workflow requirements to support the transition from bridge solution to long-term architecture Required Qualifications
• Bachelor's degree in Computer Science, Data Engineering, Information Science, Life Sciences Informatics, Chemistry, or a related field; Master's degree preferred
• 5+ years of experience in data engineering, knowledge engineering, or scientific informatics, including building data pipelines, ETL/ELT processes, or document/data extraction solutions
• Hands-on experience designing ontologies, taxonomies, or semantic data models
• Understanding of pharmaceutical stability programs and workflows (protocols, storage conditions, pull points, test methods, specifications, OOT/OOS) and the ICH Q1 guideline family
• Hands-on experience with PDF/document parsing and extraction (e.g., OCR, layout-aware extraction, table extraction from unstructured or semi-structured PDFs)
• Familiarity with regulated (GxP) data environments, including audit trail, traceability, data integrity (ALCOA+), and access-control requirements
• Proficiency in Python (or similar) and SQL for data engineering and automation
• Experience with relational, document, and/or graph databases, and integrating data from multiple source systems
• Strong communication skills to translate between CMC scientists and technical teams, and to work directly with cross-functional stakeholders
• Comfort working in an agile, discovery-driven environment with evolving scope Preferred Qualifications
• Direct experience in pharma/biotech CMC domains (stability studies, analytical chemistry, manufacturing data, specifications, or reference standards)
• Familiarity with industry standards such as the Allotrope Foundation Ontologies / Allotrope Data Format, Pistoia Alliance CMC process ontology, or FAIR data principles
• Experience with ontology editors and graph platforms (e.g., GraphDB, Stardog, Neo4j, Amazon Neptune)
• Experience configuring or integrating stability management systems or LIMS stability modules, or platforms such as Benchling, SharePoint, JMP, or Spotfire
• Familiarity with stability statistics and shelf-life estimation approaches (e.g., ICH Q1E regression analysis)
• Exposure to AI/ML- or LLM-assisted document extraction, knowledge-graph-grounded AI, or natural-language querying
• Experience working with CDMOs or other external data-generating partners
• Familiarity with regulatory submission structures (eCTD / CTD Module 3) and computer system validation (CSV/CSA) practices
• Background in proof-of-concept or pilot delivery within a build-vs-buy-vs-integrate decision process Technical Skills & Tools Languages : Python (primary), SQL, SPARQL; Cypher a plus Knowledge graphs Graph databases / triple stores (e.g., GraphDB, Neo4j, Amazon Neptune) Industry standards Allotrope Foundation Ontologies (AFO), Pistoia CMC process ontology, FAIR principles, ICH Q1/Q1E/Q6 terminology Document/PDF extraction OCR, layout-aware parsing, table extraction libraries Data platforms Data lake / data catalog tools, ETL/ELT frameworks Stability & scientific systems Stability management systems / LIMS stability modules, Benchling (exposure preferred) Analytics & visualization JMP, Spotfire, Excel Collaboration/storage SharePoint Governance Access control, audit trail, lineage, and traceability frameworks for GxP environments; ALCOA+ Emerging AI-assisted extraction, knowledge-graph-grounded AI, natural-language querying (nice-to-have exposure)