My Projects

A collection of work showcasing my skills in AI and development.

Internal Back Office Platform

Internal Back Office Platform

Everything arriving through a company website handled through to a signed quote, a sent invoice and a matched bank payment. Built end to end as the sole engineer, with its own e-signing flow, open-banking reconciliation and cookieless analytics.

Node.js Postgres Playwright Railway
AI Assistant Inside a Client's Azure Tenant

AI Assistant Inside a Client's Azure Tenant

A Microsoft Teams assistant that triages an inbox, drafts replies and schedules meetings, running entirely inside the customer's own Azure tenant. Every outward action is a code-enforced propose-then-confirm: the model drafts, a human presses send.

Python Microsoft Azure Microsoft Graph Docker
Risk-Assessment Tool for a Dutch Insurer

Risk-Assessment Tool for a Dutch Insurer

A 20-tab Excel risk assessment rebuilt as a web tool. An AI proposes an answer for each field with its source and exact quote, a human accepts or rejects, and the scoring is computed in code so the verdict stays reproducible.

FastAPI Postgres React 19 TypeScript
AI Code Security Scanner

AI Code Security Scanner

A one-day prototype: a read-only scanner that reviews a codebase for security problems. Against a purpose-built vulnerable app it found all 6 planted vulnerabilities plus 2 real ones, with zero false positives.

FastAPI Claude Agent SDK Next.js
Educational Content Generation Platform

Educational Content Generation Platform

An end-to-end GenAI-powered platform that transforms documents into CEFR-leveled language learning materials with automated text simplification and exercise generation.

Python Streamlit OpenAI
Legal AI Chatbot with RAG

Legal AI Chatbot with RAG

A RAG-based legal assistance chatbot that autonomously resolves inquiries through automated initial consultations and intelligent inquiry classification.

Python Microsoft Azure RAG Streamlit
NLP Pipeline for Safety Analysis

Identifying Workplace Accidents in News Articles

Developed a high-accuracy NLP pipeline using fine-tuned BERT models to automatically identify and classify workplace accidents in large-scale news corpora, achieving 0.89 F1-score for research at TNO.

Python BERT RoBERTa NLP
Jargon-Aware Medical Text Simplification

Jargon-Aware Medical Text Simplification

Research on automatic biomedical jargon detection and LLM-based text simplification. Evaluates cross-dataset transfer learning, establishes baselines on PLABA and MedReadMe datasets, and explores prompting strategies for medical text accessibility.

Python BERT RoBERTa LLMs
Graphair: Fair Graph Augmentation for Representation Learning

Graphair: Fair Graph Augmentation for Representation Learning

Comprehensive reproduction and extension of Graphair, a fairness-aware graph augmentation method using adversarial learning, contrastive learning, and reconstruction regularization to reduce bias while preserving informativeness in GNNs.

Python PyTorch GNNs
Medical Multimodal Segmentation Using Foundation Models

Medical Multimodal Segmentation Using Foundation Models

Comprehensive reproduction and extension of SegVol, a foundation model for 3D medical image segmentation. Evaluates geometric robustness to rotations and proposes novel group equivariant patch embeddings for enhanced rotation invariance.

Python Vision Transformers Medical Imaging
What Do YuE's Attention Heads Hear?

What Do YuE's Attention Heads Hear?

Probing musical characteristics in YuE, a generative music model. Investigates genre-specific attention patterns across Jazz, Metal, Pop, and Classical, revealing deeper layers' stronger activations and semantic-genre links, while uncovering biases toward certain prompt words.

Python Transformers Music Generation
A Dashboard for Optimizing Prompts in Large Language Models

A Dashboard for Optimizing Prompts in Large Language Models

Interactive dashboard for prompt engineering optimization in LLMs. Features dataset visualizations, prompt experimentation tools, attention score insights, and performance evaluation through confusion matrices to enhance text classification accuracy.

Python Streamlit TinyLlama