Applied AI & Engineering
AI Engineer & Data Scientist designing and deploying robust, end-to-end AI systems across healthcare, industry, and applied research environments. I specialize in translating machine learning, computer vision, and signal processing methods into solutions that are not only accurate, but deployable and impactful in real-world workflows.
My experience spans clinical AI, biomedical imaging, industrial computer vision, and applied research. All projects are documented in a structured logbook, providing traceable evidence of systems and applied research.
Professional Experience
Data Scientist — Faculty of Medicine, University of Chile
Neurosystems, SCIANLab & AudioBrain (2019–2025)
- Led the development and deployment of end-to-end AI systems integrated into clinical workflows.
- Designed machine learning and computer vision solutions for diagnostics, biomedical imaging, and cognitive health assessment
- Applied signal processing and statistical modeling to physiological and clinical data
Applied Research Engineer — University of Chile
(2009–2018)
- Developed computer vision and automation systems in industrial environments (mining, retail)
- Contributed to industry-funded R&D projects, supporting technology transfer and deployment of real-world systems
Selected Projects and Impact
Clinical AI & Biomedical Imaging
- 2nd Place – Cell Tracking Challenge: Developed high-accuracy Deep Learning models for 3D nuclei segmentation.
- RaViTT: Engineered a Vision Transformer architecture tailored for biomedical image classification.
- Glaucoma Diagnosis Pipeline: Integrated physiological signals with predictive modeling for early clinical detection.
- VolumePeeler: Created a FIJI plugin for 3D visualization and quantification of complex biological datasets.
Industrial AI & IoT
- IoT Behavioral Analysis Platform: Orchestrated real-time integration of hardware, computer vision, and control systems.
- Industrial Automation (Mining/Retail): Designed computer vision systems for process optimization and automated monitoring.
Signal Processing & Cognitive Health
- Postoperative Risk Prediction: Combined spectral analysis of EEG data with ML to predict clinical outcomes.
- Auditory Biomarkers: Developed signal-processing methods for early detection of cognitive decline.
Core Capabilities
- End-to-end machine learning systems (data → modeling → deployment)
- Computer vision: detection, segmentation, real-world systems
- Signal processing: EEG, physiological data, time-series modeling
- Deep learning: CNNs, Transformers, biomedical imaging
- Applied AI in healthcare and industrial environments
Open-Source & Tool Development
- Developed reusable, modular pipelines for:
- Biomedical image analysis
- Microscopy data processing
- Industrial computer vision systems
- Focus on reproducibility and interdisciplinary usability
Technical Skills
- Programming: Python, R, MATLAB
- Libraries & Tools: PyTorch, TensorFlow, scikit-learn, OpenCV, FIJI/ImageJ
- Practices: model evaluation, reproducibility, ethical AI, data privacy
Collaboration & Impact
- Worked with multidisciplinary teams including engineers, clinicians, and domain experts
- Translated technical results into actionable insights for decision-making
- Delivered deployable AI solutions under real-world constraints
- Bridged academic research and applied industry solutions
Context
This page focuses on applied and deployed systems.
For a structured view of projects and technical work over time, see the Professional Logbook.
For teaching and academic activities, see Teaching.