Pattern Agentix is seeking a skilled engineer to design and develop a comprehensive knowledge graph that spans multiple biological domains—including molecular biology, biochemistry, biophysics, immunology, virology, pharmacology, and computational biology.
The goal is to integrate heterogeneous datasets (ontologies, public databases, scientific literature) into a scalable, semantically rich graph that supports hypothesis generation and interdisciplinary research.
Responsibilities:• Architecture & Design:- Develop a scalable knowledge graph architecture using graph databases- Design data models to capture entities (e.g., genes, proteins, chemical compounds, immune markers) and their relationships.• Data Integration & Curation:- Integrate data from domain-specific ontologies (e.g., Gene Ontology, Ch EBI) and public repositories (e.g., Uni Prot, PDB).- Build API connectors and automation pipelines for data ingestion.- Leverage NLP tools to extract relationships from scientific literature with validation by domain experts.• Collaboration & Documentation:- Work closely with interdisciplinary teams and domain experts to ensure semantic accuracy.- Document data models, integration methods, and curation guidelines.
Requirements:• Proven experience in knowledge graph development and graph databases• Strong programming skills (Python, Java, or similar) and experience with API development.• Familiarity with semantic web technologies (RDF, ) and ontology management tools• Solid background in bioinformatics, computational biology, or related disciplines.• Demonstrated ability to work with heterogeneous data sources and interdisciplinary projects.
Contract We are seeking part time or full time on contract and will compensate to local norms. ₹6 L - ₹12 L/yr
