Coming from 5 years of experience being a Tech Leader & Software engineering
🌐 Portfolio: kateincoding.github.io/kateincoding
Brief:
- 🔬 Currently researching AI safety — building red-teaming agents and using mechanistic interpretability to detect multi-turn jailbreak attacks on LLMs.
- 🎓 Pursuing an MSc in Data Science (La Salle — Universitat Ramon Llull), with a thesis on interpretability in multi-turn jailbreak attacks.
- 🤖 Working as a Machine Learning Engineer — production ML systems, data pipelines, and full-stack development.
- 🌱 Interested in interpretability, LLM evaluation, red-teaming, and trustworthy ML.
- 💬 Ask me about starting a career in tech or moving from engineering into AI safety research.
- 📫 How to reach me: @kateincoding on twitter or on my medium!
- Languages: Python, C, JavaScript, NodeJS, SQL
- ML/Data: PyTorch, Polars, H2O AutoML, mechanistic interpretability
- Backend Frameworks: JavaScript -> [Nodejs, express, nest], Python -> [flask, django]
- Frontend Frameworks: React, Vuejs
- Cloud: AWS <3
