Graph RAG - Knowledge Engineer

Skills & Expectations
5–9 years of software engineering experience, including hands-on experience building production knowledge graphs and applied NLP systems.
Strong Python development skills, with experience building production APIs and services using Python and FastAPI.
Strong expertise in entity and relation extraction, Named Entity Recognition (NER), entity resolution/matching and semantic normalization.
Experience designing ontologies, taxonomies and graph schemas to represent complex business and domain relationships.
Hands-on experience with Neo4j and/or Amazon Neptune, including Cypher/openCypher for graph querying and traversal.
Practical experience building GraphRAG and graph + vector hybrid retrieval solutions for AI/GenAI applications.
Experience designing and optimizing graphs at millions-of-nodes/edges scale, with focus on query performance, data quality and scalability.
Strong understanding of building production data pipelines using AWS S3, ECS/EKS and Bedrock, with Docker, pytest, Git and CI/CD.
Biomedical ontology experience with standards such as UMLS, MeSH, SNOMED, RxNorm, ICD-10, DrugBank and/or ChEMBL is highly preferred.
Pharma, Life Sciences or Healthcare domain experience is preferred, particularly experience working with scientific, clinical or drug-related data.
Expected to bring strong ownership across the lifecycle—from NLP extraction and graph construction through retrieval, GenAI integration, evaluation and production operations.

Work arrangement
No