Santiago Calderón-Peña
Santiago Calderón-Peña
ML Engineer and Researcher

Machine learning engineer and researcher specializing in Computer Vision, Generative AI, and Explainable AI. I design and deploy ML systems that combine research rigor with production reality. 4+ years building models and systems that work at scale across vision, language, and multimodal domains. Fluent in English (C2), French (B2), Spanish (Native), with working knowledge of German and Italian.

View Full CV Get in touch
Featured Work
IncX

IncX
Thesis (92/100)

A Python library for tracking and visualizing real-time explanations of video content. Built as my MSc thesis research, it interprets how object detection models make decisions frame-by-frame using YOLOv10 with incremental explainability methods.
IncX Web Application

IncX Web Application

Interactive web application for real-time video object detection and explanation visualization. Demonstrates how to bring research-grade explainability methods to production, enabling stakeholders to understand AI decisions as they happen.
Latest Research
Explainable AI for the Classification of Brain MRIs

Explainable AI for the Classification of Brain MRIs
ECAI 2025 Workshop on EXPLIMED

Nathan Blake, Hana Chockler, David A. Kelly, Santiago Calderón-Peña*, Akchunya Chanchal

We performed an analysis of explainable AI tools in a medical setting, demonstrating the significant advantages of ReX, a newly introduced tool at King's College London.
Real-time incremental explanations for object detectors

Real-time incremental explanations for object detectors
Under Review

Santiago Calderón-Peña*, Hana Chockler, David A. Kelly

Existing black box explainability tools for object detectors rely on multiple calls to the model, which prevents them from computing explanations in real time. In this paper we introduce IncX, an algorithm for real-time incremental approximations of explanations, based on linear transformations of saliency maps.
© 2026 - Santiago Calderón-Peña