Description

I make AI trustworthy enough to act in the physical world. Over a TU Delft PhD and a couple of peer-reviewed papers, I built end-to-end systems that take raw sensor data and turn it into uncertainty-aware decisions for safety-critical assets in aviation, defence, and manufacturing, exactly the reliability problem AI is now hitting at scale.

As Co-Founder & CEO of Prognora, I am translating this expertise into a commercial ML decision-support platform for condition monitoring across aviation, defence, maritime, and heavy industry; sectors where an unplanned failure is measured in downtime that cannot be scheduled and consequences that cannot be undone.

Good fit for: predictive maintenance and condition monitoring systems, anomaly/fault detection on sensor data, remaining-useful-life prediction, uncertainty-aware ML for regulated or safety-critical products, and turning a research prototype into something production-ready.

Where most ML engineers stop at a notebook, I focus on what survives in production: model robustness, calibration, edge-case behaviour, and integration with maintenance workflows.

Industry field of expertise

Languages

Greek
Native or bilingual
English
Fluent

Workplace preferences

Remote only

Primarily works remotely

Prognora
Co-Founder & CEO
TECH
June 2025 - Today (1 year)
Delft, Netherlands
• Founded and lead a deep-tech startup commercializing peer-reviewed PHM/SHM research from academic methods into production-grade ML systems for industrial assets.
• Direct technical architecture, model validation, and deployment of condition monitoring and predictive maintenance pipelines for industrial pilot engagements.
• Lead commercial strategy, customer discovery, and go-to-market across aerospace, wind energy, defence, and adjacent heavy-asset industries. First-hand visibility into buyer dynamics, budget cycles, and adoption barriers in industrial AI.
• Build and lead a multidisciplinary founding team spanning ML research, software engineering, and domain expertise.
CEO Deep Learning Team management Technical project management Project owner
Delft University of Technology, Faculty of Aerospace Engineering
PhD Researcher — AI for Predictive Maintenance
AVIATION AND AEROSPACE
May 2021 - April 2025 (3 years and 11 months)
Delft, Netherlands
• End-to-end doctoral research: raw sensor data → fault detection → RUL estimation → maintenance scheduling.
• Developed diagnostic and prognostic deep learning models on multivariate time-series, image, and tabular data for composite aerospace structures.
• Designed Post-Prognosis Decision Making frameworks using Deep Reinforcement Learning under uncertainty and imperfect maintenance assumptions.
• Affiliated with the Center of Excellence in AI for Structures, Prognostics & Health Management (AISPHM).
• Best Work Award, 2nd International Conference on Condition-Based Maintenance in Aerospace, awarded by KLM.
Deep Learning Machine learning Data analysis Technical project management Python
University of Patras
Research Associate — Deep Learning for SHM
MECHANICAL ENGINEERING
May 2019 - May 2020 (1 year)
Patras, Greece
• Developed neural network models for vibration-based damage detection on aerospace structures under assembly uncertainty.
• MSc thesis graded 10/10; foundation for subsequent PhD research direction.
Machine learning Deep Learning Python Data science