Wout Vossen

vossen.w@hotmail.com

Welcome

Wout Vossen

Hello, welcome to my personal homepage! I love building products at the intersection of AI and Software Engineering. This page showcases some of my personal projects and experiences.

Education

  • Bachelor's in Psychology, KULeuven, 2015-2018
  • Bachelor's in Computer Science, KULeuven, 2018-2021
  • Master's in Engineering, Computer Science (Option AI), KULeuven, 2021-2023

My professional experience

Data Scientist

CM (Christelijke Mutualiteit)

2024 - Present

At CM, I develop AI-driven solutions to enhance organizational processes. Our team handles the entire product lifecycle, focusing mainly on NLP projects.

Key Contributions:

  • Built and deployed an API for email forwarding and reply suggestions.
  • Data extraction from medical documents and reports.
  • Developed an AI assistant using RAG to help employees understand internal documentation.
  • Currently designing an AI assistant framework to build all future assistants.

Most Used Technologies:

PythonFastAPINLP (TensorFlow, Hugging Face)GenAI (OpenAI, Anthropic)AWS (SageMaker, ECS, Bedrock, Lambda, S3, ...)Terraform

I also wrote some papers

Zero-shot recommendation as language modeling (Sileo, Vossen, Raymaekers, 2022)

This grew out of a bachelor thesis I did together with a friend. We wrote this when GPT-3 was just released and compared the capabilities of llms to generate movie recommendations with specialized matrix factorization models. It eventually got published at European Conference on Information Retrieval.

Link to publication

The effect of personalizing a psychotherapy conversational agent on therapeutic bond and usage intentions (Vossen, Szymanski, Verbert, 2023)

For my computer science master thesis I wanted to combine my psychology background with my AI skills. I developed a personalizabe chatbot agent that aimed at helping people with their mental health. The topic of this paper was to analyze the effect that personalization of such a psychotherapy conversational agent has on the therapeutic bond and usage intentions of the users. I got the opportunity to present this project at IUI 2024 in South Carolina 🤠

Link to publication

What I like to do besides coding

Personal Projects

I enjoy working on personal projects that solve problems I'm facing or find interesting. Here are some projects I've developed and launched publicly.

FireUp

FireUp

FireUp is a mobile app that helps you come up with new startup ideas. Paul Graham said the best startup ideas come from problems the founders themselves faced. So I wanted to create an app which allowed me to track my daily annoyances. It also includes AI functionality to turn those annoyances into startup ideas feasible for solo founders or small teams.

React NativeExpoGoogle Cloud (Firebase)OpenAIRevenueCat

CREV

CREV

CREV is a Go-based CLI tool designed to get AI-powered code reviews from your terminal. The idea came from my frustration with manually copying code into ChatGPT or Claude to get feedback on my projects. Although ChatGPT could provide me with useful suggestions, it lacked the full context of my project, which often resulted in incomplete reviews since it didn’t know my entire directory structure and the content of all the files. I wanted to fix that, while also eliminating the constant switching between VSCode and my browser.

GoGoReleaserGitHub ActionsOpenAINextJSTailwind CSSGoogle Cloud (Firebase)

PsyScribe

PsyScribe

An AI mental health assistant that helps you organize your thoughts and feelings. This project grew out of my interest to combine my psychology background with my software engineering skills. With the OpenAI api just released, I thought it was the perfect time to start this project.

ReactChakra UIChatGPTFlaskGoogle Cloud (Firebase)