Skills & Technologies

Current Research Stack
PhD Methods

Parallel Text & Transformation

Dataset registries, relation schemas, corpus construction, candidate generation, text reuse detection, semantic change, and transformation-spectrum analysis.

Hybrid Extraction

Rule-Based + LLM Pipelines

Structured extraction from messy humanities text, field normalisation, retry pipelines, proxy evaluation, agreement metrics, and manual audit workflows.

Agentic Systems

Language-Mediated Trust

Intent preservation, agent handoffs, tool-use traces, Logfire observability, MCP boundaries, and language-to-action drift in cyber-physical systems.

Languages & Core Tools
Python SQL Java JavaScript R C# VBA Git Jupyter LaTeX
NLP, LLMs & Evaluation
HuggingFace Transformers SentenceTransformers / SBERT spaCy Gensim NLTK OpenAI API Anthropic API Ollama Prodigy Prompt Engineering LLM Evaluation LLM Retry Pipelines Text Reuse Detection Semantic Change Analysis Rule-Based Parsing Lexical Extraction Field Normalisation Schema Design
Corpus, Retrieval & Large-Scale Data
Corpus Engineering Dataset Registries JSONL Parquet DuckDB TF-IDF Retrieval BM25 ANN Search Candidate Generation Similarity Scoring Coverage Analysis Audit Resolution
Machine Learning & Data Science
PyTorch TensorFlow Keras scikit-learn XGBoost Topic Modeling Clustering Sentiment Analysis Classification Statistical Analysis
Visualization & Analytics
Relation-Space Exploration Streamlit Power BI Tableau Qlik Sense Plotly Matplotlib Seaborn DAX Interactive Dashboards Visual Analytics Knowledge Graphs GraphViz TikZ Figures PowerPoint Automation
Cloud, Data & Observability
Azure Databricks Azure Synapse Azure Blob Storage Azure Logic Apps Power Automate AWS EC2 AWS DynamoDB AWS Kinesis MongoDB Atlas Logfire MCP Tooling Trace Analysis Pydantic AI Traces Experiment Manifests Schema Inference
Research & Collaboration
Technical Writing LaTeX Manuscripts Workshop Papers Conference Presentations Experiment Design Proxy Evaluation Manual QA Research Presentations Teaching Stakeholder Communication Business Analysis Process Design