---
title: Stefania Druga
category: people
role: Research Scientist
company: Sakana.ai
linkedin: "https://www.linkedin.com/in/drugastefania/"
twitter: "https://x.com/Stefania_druga"
website: "https://stefania11.github.io/"
sourceLabels:
  - Official speaker roster
  - Official conference schedule
last_auto_summarized: '2026-07-04T08:21:12.782Z'
---
# Stefania Druga

## Profile
Research Scientist at [[sakana-ai|Sakana.ai]], where she works on novel AI architectures beyond the transformer.

- [LinkedIn](https://www.linkedin.com/in/drugastefania/)
- [X / Twitter](https://x.com/Stefania_druga)
- [Website](https://stefania11.github.io/)

## Biography
Stefania Druga is a Research Scientist at Sakana AI in Tokyo, Japan, focused on new model architectures and long-running AI systems. At AI Engineer World's Fair 2026, she is scheduled on the Memory & Continual Learning Main Stage for “Memory Harnesses for Long-Running Research Agents,” connecting her current [[sakana-ai|Sakana.ai]] work with practical questions around agent memory, research workflows, and continual learning. Previously, she worked at Google DeepMind on novel multimodal AI applications and completed a Ph.D. in Creative AI Literacies at the University of Washington Information School.

## Conference Sessions
- [[2026-06-30-stefania-druga-memory-harnesses-for-long-running-research-agents]] — Memory Harnesses for Long-Running Research Agents (2026-06-30, 11:40am-12:00pm)

## Evidence Graph
This evidence graph summarizes how this person appears across the conference source graph: scheduled sessions, linked videos, transcripts, and slide-derived evidence.

### Linked Sessions
- [[2026-06-30-stefania-druga-memory-harnesses-for-long-running-research-agents|Memory Harnesses for Long-Running Research Agents]]

### Media Signals
- `youtube-wNH3q9pqn0U` — 2 slide-derived text signals
- Slide-derived themes for `youtube-wNH3q9pqn0U`: sound, request, beaker, crystals.
- Evidence links for `youtube-wNH3q9pqn0U`: [[youtube-wNH3q9pqn0U]], [[youtube-wNH3q9pqn0U-slides]], [[youtube-wNH3q9pqn0U-dense-slides]], [[youtube-wNH3q9pqn0U-reconstructed-slides]]