Scientific data engineering
I build robust pipelines for ingestion, synchronisation, quality control, harmonisation, and analysis of structured research datasets.
I work across physiological, behavioural, and environmental data. My focus is on building reliable workflows for synchronisation, quality control, documentation, and downstream analysis in collaborative research settings.
My background combines Python-based data engineering, multimodal analysis, and scientific workflow design in interdisciplinary academic environments.
I build robust pipelines for ingestion, synchronisation, quality control, harmonisation, and analysis of structured research datasets.
I work with physiological, behavioural, and environmental signals, including protocol-based human-subject studies and wearable sensor data.
I support interdisciplinary teams with analysis documentation, publication-oriented outputs, and reusable software workflows.
The future of intelligent systems will depend on richer sensing, better alignment between environment and physiology, and workflows that make complex human data usable at scale. My work sits in that layer between sensing and intelligence.
The strongest threads in my work are multimodal data integration, signal processing, data curation, feature extraction, validation, and research coordination.
A modular research software framework for synchronized preprocessing, feature extraction, quality control, and temporal analysis of physiological and environmental time-series data.
See project detailsA multimodal cognitive neuroscience study integrating EEG, HRV, EDA, and auditory stimulation with structured operational design and protocol-aligned analysis.
See project detailsA human-centred multimodal study linking physiological, environmental, and perceptual data through synchronized acquisition, preprocessing, quality control, and protocol-aware analysis.
See project details