Design, build, and operate the data infrastructure for a clinical trial design platform that extracts insights from clinical protocols, regulatory documents, and published articles to accelerate trial design decisions. This role owns the pipelines that ingest, parse, transform, and serve clinical data - from raw PDF extraction through structured storage in Aurora and GraphDB, to serving curated knowledge for LangGraph-based agentic AI workflows.
Requirements
- Build ingestion pipelines for clinical trial protocols, ICF documents, SmPCs, CSRs, and published articles (PubMed, CTIS, ClinicalTrials.gov) - handling PDF parsing, text extraction, and structured data normalization
- Design and implement data models in Amazon Aurora (relational) and GraphDB (knowledge graph) to represent trial design entities: endpoints, eligibility criteria, study arms, interventions, therapeutic areas, and their relationships
- Develop embedding and vectorization pipelines to prepare extracted clinical text for RAG-based retrieval in LangGraph agentic workflows - chunking strategies, metadata enrichment, and vector store population
- Build and maintain ETL/ELT workflows that transform unstructured clinical content into queryable, linked data across both relational and graph stores
- Implement data quality validation specific to clinical data - protocol section classification accuracy, entity extraction completeness, cross-reference integrity (NCT IDs, EudraCT numbers, MeSH terms)
- Build data serving APIs (Python/FastAPI) that expose curated datasets to the Angular frontend and LangGraph agent layer
- Set up data lineage tracking and audit trails to support regulatory traceability of AI-generated trial design recommendation
- Strong Python development experience, including PDF/document parsing libraries such as PyMuPDF, pdfplumber, unstructured.io, or similar.
- Advanced PostgreSQL-compatible SQL, including Amazon Aurora; experience with schema design, migrations, query optimization, and indexing strategies for large clinical datasets.
- Hands-on experience with Neptune, Neo4j, or similar graph databases; proficiency in SPARQL or Cypher; experience with ontology and knowledge graph modeling for biomedical entities.
- Experience with AWS services including Aurora PostgreSQL, S3, Lambda, Step Functions, SQS/SNS, and IAM, particularly for data pipeline orchestration.
- Experience with PDF text extraction, document section classification, and named entity recognition (NER) for clinical/biomedical text; familiarity with embedding models and vector stores such as OpenSearch, pgvector, or Pinecone.
- Experience building data-serving APIs using FastAPI, including asynchronous programming patterns and backend integration.
- Experience preparing data for LangChain/LangGraph applications and designing RAG pipelines, including chunking, retrieval, reranking, and prompt-data integration.
- Experience with Airflow, Prefect, AWS Step Functions, Temporal, or similar workflow orchestration tools; ability to design multi-stage DAGs with dependency management, retry logic, monitoring, and error handling.
- Experience with Terraform or AWS CDK, Docker, and Git, including automated pipeline testing and deployment on AWS.
Domain Knowledge
- Understanding of clinical trial structure: protocol sections (objectives, endpoints, eligibility criteria, study design, statistical considerations)
- Familiarity with clinical data standards or terminologies (MeSH, MedDRA, SNOMED, ATC codes, CDISC) is a strong plus
- Awareness of regulatory data integrity requirements (21 CFR Part 11, EU Annex 11, ALCOA+ principles)
Nice to Have
- Experience with biomedical knowledge graphs (e.g., linking drugs -> targets -> diseases > trials)
- Prior work with PubMed/MEDLINE data, ClinicalTrials.gov API, or EMA/CTIS data.
- Apache Spark or Databricks for batch processing of large document corpora
- dbt for transformation layer management over Aurora
Benefits
CURIOSITY DRIVEN, SCIENCE FOCUSED, EMPLOYEE BUILT. Our culture is unlike any other, one where we debate, challenge ourselves, and interact with all alike. We are a curious bunch, characterized by our passion to learn and spirit of teamwork. Zifo is a global R&D solutions provider focused on the industries of Pharma, Biotech, Manufacturing QC, Medical Devices, specialty chemicals and other research-based organizations. Our team’s knowledge of science and expertise in technology help Zifo better serve our customers around the globe, including 18 of the Top 20 Biopharma companies.
We look for Science – Biotechnology, Pharmaceutical Technology, Biomedical Engineering, Microbiology etc. We possess scientific and technical knowledge and bear professional and personal goals. While we have a “no doors” policy to promote free access within, we do have a tough door to walk in. We search with a two-point agenda – technical competency and cultural adaptability.
We offer a competitive compensation package including accrued vacation, medical, dental, vision, 401k with company matching, life insurance, and flexible spending accounts.
If you share these sentiments and are prepared for the atypical, then Zifo is your calling!
Zifo is an equal opportunity employer, and we value diversity at our company. We do not discriminate on the basis of race, religion, color, national origin, gender, sexual orientation, age, marital status, veteran status, or disability status.
Skills Required
- Strong Python development experience, including PDF and document parsing libraries such as PyMuPDF, pdfplumber, unstructured.io, or similar.
- Advanced PostgreSQL-compatible SQL, including Amazon Aurora, with schema design, migrations, query optimization, and indexing experience.
- Hands-on experience with Neptune, Neo4j, or similar graph databases; proficiency in SPARQL or Cypher; and biomedical ontology or knowledge graph modeling experience.
- Experience with AWS services including Aurora PostgreSQL, S3, Lambda, Step Functions, SQS/SNS, and IAM for data pipeline orchestration.
- Experience with PDF text extraction, document section classification, named entity recognition for clinical or biomedical text, embedding models, and vector stores.
- Experience building data-serving APIs with FastAPI, asynchronous programming patterns, and backend integration.
- Experience preparing data for LangChain or LangGraph applications and designing RAG pipelines involving chunking, retrieval, reranking, and prompt-data integration.
- Experience with Airflow, Prefect, AWS Step Functions, Temporal, or similar workflow orchestration tools, including DAG dependencies, retries, monitoring, and error handling.
- Experience with Terraform or AWS CDK, Docker, and Git, including automated pipeline testing and AWS deployment.
- Understanding of clinical trial structure, including objectives, endpoints, eligibility criteria, study design, and statistical considerations.
- Familiarity with clinical data standards or terminologies such as MeSH, MedDRA, SNOMED, ATC codes, or CDISC.
- Awareness of regulatory data integrity requirements, including 21 CFR Part 11, EU Annex 11, and ALCOA+ principles.
- Experience with biomedical knowledge graphs linking drugs, targets, diseases, and trials.
- Experience with PubMed/MEDLINE data, ClinicalTrials.gov API, or EMA/CTIS data.
- Experience with Apache Spark or Databricks for large document corpus batch processing.
- Experience with dbt for transformation layer management over Aurora.
What We Do
Did you know that the saying ‘Curiosity killed the cat’ actually ends with ‘but satisfaction brought it back’? We suspect that the shortened version is the doing of grown-ups suppressing the innately curious child inside them! For us at Zifo, we take curiosity as unbounded - it is a celebrated value. Curiosity does wonderful things - drive exploration, accelerate learning, inspire better solutions, lead to innovation, drive conversations. We believe that the scientific community’s most important duty to the world is to stay curious. And this is what we do at Zifo. We have a global presence of over 1000 employees spread across our offices in US, UK, France, Germany, Switzerland, Japan, China, Canada, Singapore & India. We offer services in areas such as Scientific Informatics, Lab Informatics, Clinical Biometrics, Regulatory Compliance including Computer System Validation and Genome Informatics across 20+ countries. Our customers include 7 of the Top 10 global Bio-pharma companies. We are listed as 'Technology Fast 50' by Deloitte for 9 consecutive years (2012-2020) and as one of the 'Best Places to Work' for the past five years. We strive to stay curious, day in and day out. Asking the right questions, and listening to provide the right solutions. Write to us at [email protected].
