Knowledge Graph & AI Engineer

About AstraZeneca AstraZeneca is a global, innovation-driven BioPharmaceutical business that focuses on the discovery, development, and commercialisation of prescription medicines for some of the world’s most serious disease . But we’re more than one of the world’s leading pharmaceutical companies. At AstraZeneca we’re dedicated to being a Great Place to Work. Where you are empowered to push the boundaries of science and ignite your entrepreneurial spirit. There’s no better place to make a difference to medicine, patients, and society. An inclusive culture that champions diversity and collaboration. Always committed to lifelong learning, growth, and development! About the role We are seeking a highly skilled and experienced Knowledge Graph & AI Engineer to join the Forward Deployed AI group as part of the Knowledge Engineering Team . In this position you will play a critical role in supporting projects and initiatives across different domains within AstraZeneca. Your primary responsibility will be to develop and oversee the data ingestion , clean-up, and enrichment part of the pipeline for projects that require it. The ideal candidate will possess solid experience in data engineering and analytics, complemented by demonstrated experience in applying AI within healthcare or biological domains. Key r esponsibilities Work closely with data scientists, knowledge engineers, domain experts and other teams to understand their data needs and translate them into clear, manageable technical tasks. Support the design, implementation and maintenance of data ingestion pipelines under the guidance of senior engineers. Contribute to the implementation and running of reliable, scalable ETL/ELT workflows to ingest, transform and load data. Assist with data cleansing, normalisation and transformation activities to prepare datasets for analysis and downstream use. Help enrich datasets by applying basic knowledge graph techniques and integrating reference data and ontologies. Apply sound data engineering practices and ontology design principles to help keep the Knowledge Graph structure accurate , consistent and aligned with project requirements. Write and optimise Cypher and SQL queries to support data validation, enrichment and analysis requests. Develop and run basic data quality checks and validation routines, escalating issues where necessary. Support the preparation and deployment of AI and ML solutions, particularly those that make use of knowledge graphs and LLM-powered applications. Support the setup and integration of the Knowledge Graph with LLM-powered applications and related services. Help monitor and troubleshoot data pipelines and services, resolving straightforward issues and escalating more complex problems. Document data models, ingestion workflows, query patterns, standards and procedures to ensure work is clearly recorded, reproducible and easy to share within the team. Provide demos and support to internal stakeholders on how to access, query and interpret data within the Knowledge Graph. Participate in continuous improvement activities, learning from feedback and contributing to enhancements of tools, pipelines and team practices. Requirements Bachelor’s or Master’s degree in Computer Science , Engineering, or a related field. Basic proficiency in Python for data processing and scripting . E xperience building or supporting data pipelines such as ETL/ELT . Familiarity with relational databases and SQL . Exposure to knowledge graphs or graph databases, gained through projects or coursework . Understanding of core concepts in data cleansing, normalisation and enrichment . Exposure to AI/ML concepts and libraries through academic, personal or internship projects . U nderstanding of software engineering practices such as version control and testing . Interest in applying data and AI techniques to health