Clinical Study Data Engineer – AI & Graph Pipelines

Roche; Hyderabad City Taluka; Vor Ort; PKR 1.800.000 - 3.600.000; Vollzeit

Zusammenfassung

Roche seeks a Data Engineer – Clinical Study Design to build the data foundation behind Study Designer, translating complex clinical data into scalable pipelines that power design insights.

The role combines data engineering with clinical data workflows, NLP document processing, and API development to serve a frontend and LangGraph workflows while ensuring regulatory traceability of AI recommendations.

Qualifikationen

• Bachelor's degree in Computer Science or data engineering or related field.
• 5–8 years of production data platforms experience.
• Experience with biomedical knowledge graphs and clinical data sources.

Aufgaben

• Build ingestion pipelines for clinical trial protocols and related documents.
• Design data models for trial design entities and their relationships.
• Develop embedding pipelines for RAG-based retrieval in LangGraph workflows.
• Create ETL/ELT pipelines to unify data across relational and graph stores.
• Implement data quality validation and data lineage for regulatory traceability.
• Build data serving APIs with Python/FastAPI for frontend and LangGraph layers.

Kenntnisse

Python

SQL

NLP / Document Processing

FastAPI

AI/ML Data Infrastructure

Pipeline Orchestration

Data Modeling

AWS

Ausbildung

Bachelor's degree in Computer Science or Data Engineering

Tools

Aurora

GraphDB

Neptune / Neo4j

OpenSearch / pgvector / Pinecone

PubMed/ClinicalTrials.gov data tools

Jobbeschreibung

Roche seeks a Data Engineer – Clinical Study Design to build the data foundation behind Study Designer, translating complex clinical data into scalable pipelines that power design insights.

The role combines data engineering with clinical data workflows, NLP document processing, and API development to serve a frontend and LangGraph workflows while ensuring regulatory traceability of AI recommendations.