PhD researcher working across computational literary studies, applied AI, and research-oriented software systems.
My current technical work centers on computational NLP, local language-model and retrieval workflows, structured data and provenance, and software projects developed through explicit specifications, validation, testing, and reproducible repository state.
I work primarily at the intersection of computational text analysis, local and open-source LLM systems, retrieval-augmented knowledge workflows, and research software.
I am particularly interested in systems where source provenance, data-authority boundaries, privacy, reproducibility, and reliable model-mediated interaction matter as much as model capability itself.
My development workflow is specification and validation-led, with coding agents used for implementation alongside repository-level constraints, tests, review, and explicit acceptance criteria.
A non-LLM Python text-generation system built around structured JSON data, deterministic seeded generation, thematic constraints, CLI workflows, corpus validation, and regression tests.
A small client-side web application with transparent calculation rules, methodological documentation, shareable state, GitHub Pages deployment, and regression testing.
My academic background is in literature, with current research interests spanning computational literary studies, multilingual text analysis, narratology, intertextuality, and scholarly research workflows.