Burcu Sayin Günel
Trento, Italy
applied AI · research × industry

Burcu Sayin Günel

Applied Research Scientist  ·  CTO, Stealth AI Startup

I build trustworthy AI systems — turning research on LLMs, conversational AI, and human-AI collaboration into products that ship. PhD from the University of Trento, 30+ peer-reviewed publications, and a growing focus on bringing AI research into real-world applications.

LLMs NLP Human-AI Collaboration Trustworthy AI Python · PyTorch
250+
Citations
9
h-index
30+
Publications
3×
Best-Paper Awards
About

Research depth, shipped at industry pace

I work at the intersection of large language models and human decision-making — building AI systems reliable enough to trust, and understanding precisely when they shouldn't be.

I'm an applied research scientist working at the intersection of large language models and human decision-making. After completing my PhD cum laude at the University of Trento and a PostDoc with the Structured Machine Learning Group, I now lead AI strategy and engineering as CTO of a stealth-stage startup — designing LLM-powered systems that are reliable enough to put in front of real users. My work spans hybrid human-machine collaboration, NLP, and the science of when (and when not) to trust a model.

Experience

Where I've worked

Mar 2026 — Present

Chief Technology Officer

Stealth AI Startup
  • Lead AI/ML strategy, architecture, and engineering for an early-stage startup company.
  • Design and ship LLM-based systems — from retrieval pipelines and evaluation to deployment.
  • Translate frontier research on trustworthy and human-aligned AI into production-grade features.
Nov 2022 — Feb 2026

Postdoctoral Researcher

Structured Machine Learning Group · University of Trento
  • Researched hybrid human-LLM reasoning and decision-making within the EU Horizon TANGO Project.
  • Built reliable retrieval (RAG) methods for large legal and medical corpora, and clinical NLP systems.
  • Studied LLM trustworthiness — consistency across languages, model correction, and learning to reject.
2018 — Sep 2022

Ph.D. in Information & Communication Technology (cum laude)

University of Trento
  • Thesis: “Towards Reliable Hybrid Human-Machine Classifiers.”
  • Active learning over crowdsourced data, ML calibration, and the science of rejection.
Jan 2016 — Sep 2018

Research & Teaching Assistant

Izmir Institute of Technology · Dept. of Computer Engineering
  • Conducted research on social network analysis and privacy.
  • Taught and supported courses including Operating Systems, Data Structures, Data Mining, Probability & Statistics, and Cryptography.
Research

Selected publications

202535 citations

Fostering Effective Hybrid Human-LLM Reasoning and Decision Making

How to combine human judgment with LLM reasoning so the team outperforms either alone — interaction patterns for reliable hybrid decisions.

202511 citations

Towards Reliable Retrieval in RAG Systems for Large Legal Datasets

Diagnosing and improving retrieval quality when RAG systems operate over massive, specialized legal corpora.

202418 citations

Can LLMs Correct Physicians, Yet? Investigating Effective Interaction Methods in the Medical Domain

When and how LLMs can usefully challenge expert decisions — designing safe human-AI interaction for high-stakes medicine.

202514 citations

Do LLMs Provide Consistent Answers to Health-Related Questions Across Languages?

Auditing multilingual consistency in LLM health answers — a trustworthiness lens on cross-language reliability.

202410 citations

Learning to Guide Human Decision Makers with Vision-Language Models

Using VLMs to guide rather than replace human decisions, improving accuracy while keeping humans in control.

HCOMP · Best Paper12 citations

The Science of Rejection: A Research Area for Human Computation

Why learning to reject model predictions is central to ML — and what role humans play. Blue Sky Best Paper, AAAI HCOMP 2021.

Looking for the full list? See my Google Scholar profile.
Recognition

Awards

🏆

Blue Sky Best Paper Award

AAAI HCOMP 2021

For “The Science of Rejection: A Research Area for Human Computation,” at the 9th AAAI Conference on Human Computation and Crowdsourcing.

🎖️

Methods Recognition

ACM CSCW 2021

For “On the State of Reporting in Crowdsourcing Experiments and a Checklist to Aid Current Practices.”

🥇

Best Paper Award

Data Analytics 2017

For “A Novel Approach to Information Spreading Models for Social Networks,” at the 6th International Conference on Data Analytics.

Contact

Let's build something together

Open to conversations about applied AI, research collaborations, and advisory roles.