About
Data scientist and AI engineer at Afliant. Part-time AI alignment researcher, working on the behavior of language models: chain of thought, elicitation, and red-teaming.
Previously a neuroscience researcher — I did my PhD in Munich under Ruben Portugues, describing for the first time a circuit for heading direction integration in the larval zebrafish brain (thesis), and then a postdoc at the Iurilli lab at IIT, investigating the neural bases of hunting behavior in the rodent brain.
Here are some of my talks and projects:
AI alignment #
- ARENA 9.0, Alignment Research Engineer Accelerator, London (Oct 2026)
- Leaking Muse’s Charter, Meta’s model spec: reconstructing Muse Spark Open’s model spec from its chain of thought (explorer)
- Hannibal Mistral: persona-conditioned elicitation in the Mistral model family
- Red-teaming leaderboards: top 30 on the JudgmentDay arena (AIM Intelligence), top 50 in the Gray Swan indirect prompt-injection challenge
Talks #
- Cosyne 2022: A network that integrates heading direction in the larval zebrafish brain
- Neuromatch 2020: BrainGlobe: a Python ecosystem for computational (neuro)anatomy
Open source #
- Stytra: a Python package to control stimulation and track behavior in zebrafish experiments
- BrainGlobe: a Python toolbox for morphological analyses in systems neuroscience
Teaching #
- Python for (open) Neuroscience: Python crash course for the Graduate School in Neuroscience at the University of Trento — teaching material, exercises, and lecture recordings on GitHub
- Lecture notes for the course Modelling of Cellular Physiology by Prof. Christian Leibold at LMU Munich