- 🧠 I'm a PhD Researcher in AI Safety at UC3M, collaborating with INRIA Paris and the University of Cambridge.
- 🎓 I hold a BSc in Computer Science Engineering and a Double MSc in Computer Science & Cybersecurity from UC3M, Madrid.
- 🛡️ I’ve worked on LLM compression, membership inference attacks, and steganographic signals in chain-of-thought prompting.
- 💡 I'm especially interested in:
Privacy
,AI Alignment
,LLM Steering
, andModel Optimization
. - 🏆 I've won several national hackathons on machine learning and AI.
- 🇯🇵 I spent one year in Tokyo as a researcher through the Vulcanus in Japan program.
- 🏄 I’m also a sponsored longboard rider, sharing my passion for skating and tech.
- 📨 You can reach me at: [email protected]