NLP engineer with a linguistics background (MPhil, University of Bergen). Most of my work sits at the intersection of medical text and structured knowledge including ontologies, clinical terminologies, that sort of thing.
At Nemoest AS ,I built a RAG-based document retrieval system for Norwegian legal texts. My thesis was on automating article screening for systematic reviews using ontology-enriched classification. More recently I built MedTermCheck, a tool that verifies LLM-extracted medical codes against SNOMED-CT and ICD-10.
Clinical NLP: classifying medical texts using ontology-based feature enrichment, verifying LLM outputs against structured terminologies
Legal document retrieval: RAG pipelines for Norwegian regulatory text
Explainable ML : SHAP-based interpretation for classification models in healthcare and business contexts
Python, scikit-learn, TensorFlow, SHAP, Hugging Face, Gradio, Azure, REST APIs, SNOMED-CT, ICD-10, SQL, MLflow
Certs: Azure AI Engineer Associate (AI-102), Azure Fundamentals, ML Engineer (DataCamp)
Extending my thesis classification pipeline with benchmark datasets (Cohen et al. 2006, 2,744 abstracts) and 5-fold cross-validation. Recent finding: mechanical ontology enrichment doesn't reliably improve classification with broader implications for ontology-grounded NLP.
Building out local RAG infrastructure for document retrieval workflows.