Teaching

I design and teach engineering courses that bridge theory, experimentation, and real-world systems.

I have been involved in university-level teaching since 2005, starting as a teaching assistant and progressing to leading undergraduate and graduate-level courses.

My teaching spans multiple institutions, including the Department of Electrical Engineering (DIE) at Universidad de Chile, and covers areas such as electrical engineering, applied mathematics, and AI-driven systems, including topics like image processing.

Summary

• University teaching involvement: 2005 – Present
• Course leadership and instruction: 2015 – Present
• +70 course instances (2015–2026)
• +2500 students across institutions
• Courses in engineering, mathematics, physics, and data science
• Undergraduate thesis supervision in AI, computer vision, and biomedical engineering

Selected Courses

EL3201 – Laboratorio de Ingeniería Eléctrica

Institution: Universidad de Chile (FCFM) Role: Instructor (100%) Period: 2022–2026

Core laboratory course where students transition from theoretical concepts to real experimental systems, designing, implementing, and validating electrical engineering solutions under real constraints.

The course has evolved across multiple iterations toward structured experimentation, reproducibility, and technical communication aligned with engineering practice.

Selected laboratory activities and student work:

• Student project presentations in Electrical Engineering Lab

EL5206 – Laboratorio de Inteligencia Computacional y Robótica

Institution: Universidad de Chile (FCFM) Role: Co-instructor (with Martín Adams) Period: 2021–2026

Advanced project-based laboratory course where students design and implement AI-driven systems combining machine learning, computer vision, and robotics.

The course emphasizes real-world problem solving, experimental validation, and the development of complete engineering pipelines—from data acquisition to model evaluation and system integration.

Selected projects and course outcomes:

• Final project presentations in Computational Intelligence and Robotics

These courses are tightly connected to my research and applied work, with many student projects evolving into real systems documented in my logbook and linked to ongoing research and industry projects.

Additional Teaching Experience

Universidad Santo Tomás

Recent (2025)

• Electricidad y Magnetismo
• Estática y Dinámica (including Summer term)
• Ondas, Óptica y Calor
• Elementos de Mecánica y Resistencia de Materiales

Previous (2017–2022)

• Cálculo Diferencial e Integral
• Matemáticas para la Ingeniería
• Ecuaciones Diferenciales
• Electricidad y Magnetismo

Universidad Andrés Bello

Recent (2026)

• Matemáticas 1
• Matemáticas 3

Previous (2015–2019)

• Álgebra
• Cálculo
• Introducción a las Matemáticas

Universidad del Desarrollo (UDD)

• Deep Learning (Master in Data Science)

Early Teaching Experience – Universidad de Chile

Department of Electrical Engineering (DIE)

• Laboratorio de Sistemas Digitales (2011–2019)
• Señales y Sistemas (2012–2017, 2015)
• Introducción al Procesamiento Digital de Imágenes (2011–2017)
• Sistemas Digitales (2011–2013)
• Sistemas para el Procesamiento de la Información (2010)
• Laboratorio de Electrónica (2009–2011)

Department of Mathematical Engineering (DIM)

• Álgebra Lineal (2007)
• Cálculo Numérico (2005–2007)
• Laboratorio de Cálculo Numérico (2005–2007)

Student Supervision and Mentorship

I actively supervise undergraduate theses and research-oriented projects, primarily in computer vision, machine learning, and biomedical engineering.

My supervision focuses on guiding students through the full development cycle: problem formulation, implementation, evaluation, and communication of results.

Summary

• 10+ undergraduate theses supervised or co-supervised
• Participation in thesis committees and evaluations
• Topics spanning AI, computer vision, and biomedical applications
• Strong integration between teaching, research, and applied projects

Several of these projects are closely related to my research in computer vision, machine learning, and biomedical engineering (see Research).

Advisor – Universidad de Chile (FCFM)

• 2026: Detection and statistical analysis of shapes in sperm images using classical computer vision techniques for morphological classification Camila Maire – In progress

• 2026: Development and implementation of a computer vision system based on Transformers for vehicle identification and fraud prevention on highways Diego Vega

• 2024: Automated diagnosis of glaucoma using Machine Learning tools applied to Chromatic Pupilometry data Manuel Zamorano

• 2023: Transformer-type neural networks for classifying HER2 protein overexpression in gastric cancer biopsy images Diego Muñoz

Co-Advisor – Universidad de Chile (FCFM)

• 2026: Monitoring calving events through image processing Catalina Zapata – In progress (poster)

• 2025: Deep Learning-based segmentation and classification of sperm heads for normality evaluation Pilar Nilo

Committee Member – Universidad de Chile (FCFM)

• 2025: Segmentation and quantification of arterial calcifications in breast tomosynthesis using Deep Learning and Vision Transformers Bastián Castelli

• 2023: Intelligent image recognition engine for last-mile delivery quality control Franco Mirauda

• 2023: Detection and portion estimation of granular ingredients using computer vision Gonzalo Hernández

External Evaluator – Medical Technology, Universidad de Chile (Tech4Medics Lab)

External evaluator in thesis committees at Tech4Medics Lab, an interdisciplinary research group working at the intersection of medical imaging, artificial intelligence, and clinical decision support.

This role involves evaluating applied AI systems in real clinical contexts, reinforcing the connection between teaching, research, and deployment in healthcare environments.

• 2026: AI-based evaluation of positioning criteria in digital mammography Matías Gajardo, Carolina Bavestrello

• 2025: Breast density estimation in T1-weighted MRI using Deep Learning Vicente Cajas, Sebastián Millar

• 2024: Estimation of breast density in digital mammography and tomosynthesis using AI Francisca Bustamante, Sofía Rivas

• 2023: Quantification of vascular calcifications in breast tomosynthesis using AI Constanza Ramírez, Marcelo Flores

Internship Supervision – SCIANLab (Universidad de Chile)

• 2024: Measurement of membrane force exerted by a cell Matías Carvajal

• 2023: Development of segmentation methods with limited or low-quality training data Leslie Cárdenas

• 2023: Literature review on Transformer-type neural networks Manuel Zamorano

• 2023: Segmentation of cell nuclei using Deep Learning under jamming conditions Vanessa González

• 2022: 3D Light-sheet image rotation for embryo development visualization Magdalena Álvarez

Teaching Focus

My teaching approach is centered on:

• Laboratory-based and experiential learning
• Project-oriented evaluation
• Integration of real-world engineering problems
• Development of technical and scientific communication
• Use of AI and data-driven methods in engineering education

Many course activities are closely connected to research problems in computer vision, machine learning, and biomedical engineering.

Teaching Philosophy

I view engineering education as an active process grounded in experimentation, iteration, and problem solving.

Laboratory-based courses play a central role in bridging theory and practice, allowing students to engage directly with systems, data, and real-world constraints. My teaching emphasizes not only technical correctness, but also the ability to design solutions, communicate results, and critically evaluate outcomes.

I aim to integrate research and teaching by exposing students to contemporary challenges in artificial intelligence, computer vision, and biomedical engineering.