EuroPython 2025

Jenny Vega

Software Engineer with 8+ years of experience. Currently working at Isomorphic Labs as ML Platform Engineer building scalable and safe solutions using large models. Interested in AI Safety and AI Governance.


Sessions

07-16
13:50
60min
AI Discussion Panel
Laura Summers, Kayode Makinde, Reyha Verma, Jenny Vega

In this one-hour panel session, AI experts will explore the rapidly evolving impact of these technologies on our society. The discussion will address pressing questions across key domains being transformed by AI: privacy and regulation, environmental implications, economic and labor shifts, and the impact of AI on media and art.

Beyond hearing insightful perspectives from our panelists, you'll have the opportunity to submit your own questions throughout the session. You’ll also have the chance to walk away with prizes, through answering quiz questions based on topics discussed in the session. Whether you're an AI enthusiast, industry professional, or simply curious about how these technologies will shape our world, join us to find out more about this complex area and have your burning questions answered.

Machine Learning, NLP and CV
South Hall 2B
07-17
12:45
30min
Hacking LLMs: An Introduction to Mechanistic Interpretability
Jenny Vega

Large Language Models (LLMs) have become transformative tools, reshaping industries and research alike. Yet, while their outputs can feel like magic, their inner workings remain opaque to most users. How do these models "think"? Can we untangle the layers of their reasoning processes? Step into the cutting-edge field of Mechanistic Interpretability, where we aim to decode the black box of LLMs into understandable, human-readable components.
In this session, we will explore how researchers and practitioners dissect neural networks, uncovering the mechanisms behind their behavior. We will start with the foundational concepts, what Mechanistic Interpretability is and why it matters, before diving into practical tools and techniques.
We will emphasize why this field is essential: from ensuring models behave safely and ethically to optimizing their performance and fostering trust in AI systems. Attendees will leave with a conceptual toolkit for interpreting LLMs and practical takeaways on how to start applying these insights in their own work using Python libraries like PyTorch, Transformers, and interpretability-specific tools.
This talk assumes familiarity with AI fundamentals but introduces advanced concepts with approachable explanations. Whether you're a researcher, developer, or curious enthusiast, you’ll gain actionable insights and inspiration to engage with one of the most exciting frontiers in AI. No specialized hardware or prerequisites are required, just bring your curiosity!

Machine Learning: Research & Applications
South Hall 2B