Reporting to Dr. John Jose Nunez, the incumbent will:
• Architect and maintain scalable pipelines for the ingestion and transformation of diverse biological and clinical data types, including drug targets, approved drugs, and related ontologies.
• Design components of the AI pipeline for enrichment and reasoning over technical life sciences data using large language models (LLMs).
• Manage the storage and retrieval of biological entities and relationships using vector databases and PostgreSQL.
• Integrate specialized NLP workflows to extract insights from unstructured academic and clinical text.
• Maintain rigorous scientific and data quality standards for AI-generated outputs, ensuring contributions meet clinical and technical standards.
• Help define data engineering practices, testing strategies, and quality standards; translate product requirements into scalable technical designs and implementation plans.
• Collaborate within multidisciplinary teams across SOZO Intuition Systems and UBC/BC Cancer, including technical, clinical, and scientific stakeholders.
• Supervise research assistants and trainees involved in data collection, analysis, and related projects.
• Develop and write manuscripts for peer-reviewed publications.
• Contribute to the development of future grant applications.
• Other activities as required.