I help organizations develop effective and safe AI systems grounded in user research.
Contact | About | Projects | Services
About
I’m a researcher and analyst specializing in human-automation interaction in safety-critical environments, most recently in next-generation nuclear energy systems. I hold a phd in human-ai interaction, where I focused on how different machine learning explanations affect user reliance, trust, and workload.
My past work spans AI risk, human-machine learning interaction, and system usability across energy, insurance, telecom, and academia. You can find my academic publications here.
As of June 2025, I am a member of z-inspection, an international initiative dedicated to evaluating AI systems.
Projects
Small Modular Reactors, Human Factors Research Program
Lead Researcher, 2025
Evaluated human-automation interfaces for operation and monitoring of small modular reactors, focusing on simulations for human performance measurement and multi-unit operations.
LLMs Risk Assessment for Global Telecom Company
Consultant, 2024
Assessed generative AI systems with emphasis on safety, bias, performance, and robustness, including red teaming a RAG-based customer service application with over 16 million users.
Development of ML Interpretability Tool for Ericsson’s Data Scientists
Collaborator, 2023
Conducted user evaluations of a tool designed to help data scientists interpret results from multiple machine learning models.
Services
- User Evaluations
Assess how users interact with automated systems to improve trust and performance.
- AI Risk Assessment
Identify and mitigate safety, bias, and reliability risks.
- Training and Workshops
Equip people with practical skills in AI safety and human-centered design.
Contact
gentiledv [at] gmail [dot] com