Education

Education

MSc. Artificial Intelligence - Universidad Internacional de la Rioja

2022 - 2023

Advanced course on: Data Engineering

Thesis: Machine Learning to predict radiation detectors in Radioactive ParticleTracking Systems

Logroño - Spain

BSc. Chemical Engineering - Escuela Politécnica Nacional

2016 - 2022

Honors: Cum Laude

Technical specialization: Nuclear Applications

Quito - Ecuador

Idioms

English: C1 - Advanced Level

Spanish: C2 - Native Speaker

Soft-Skills

Life-Long learning

Teamwork

Self-motivation

Hard Skills

Deep Learning

Machine Learning

Relational Databases

Work Experience

Data Scientist - Bi Solutions
December 2022 - Today
  • I work in the production department of the company. I have carried out several projects involving code versioning, model versioning, and MLOps. In addition, I have work on-premises and on-cloud (GCP and AWS) to deploy machine learning models.
  • Predicting loan defaults using machine learning techniques in Python. I have built an MLOps architecture with Continuous Training (CT), Continuous Integration (CI), and Continuous Deployment (CD) on Google Cloud Platform (Artifact Registry, Cloud Run, Cloud Storage).
  • Predicting sales in airport stores and optimizing the gate assignment model for flights. I use CI/CT/CD to deploy models with AWS (Sagemaker, Elastic Container Registry, App Runner, S3).
  • Forecasting inventory demand and optimizing inventory levels to avoid overstocking or understocking. I deploy machine learning models in batches using GitHub Actions and Azure Databricks.
  • Tools used: Scikit-learn, Tensorflow, Numpy, Pandas, Matplotlib, Seaborn, Scikit-optimize, Google Colab, Python, AWS, GCP, Azure, Docker, GitHub Actions
Data Scientist - Freelancer
November 2022
  • I was working as a data scientist coordinating the marketing campaign for the policy. The objective was to apply the philosophy of data-driven for decision making in political campaigns.
  • Web scraping of post from social media.
  • Natural Language Processing (NLP) for sentiment analysis.
  • Data Visualization with Tableau.
  • Tools used: NLTK, Tensorflow, Tableau, Python
Machine Learning Engineer - Freelancer
March 2022 - November 2022
  • Developing regression algorithms through Feed Forward Neural Networks, Convolutional Neural Networks, and KNN regressors.
  • Hyper-parameter tunning of machine learning algorithms.
  • Tools used: Scikit-learn, Tensorflow, Numpy, Pandas, Matplotlib, Seaborn, Scikit-optimize, Google Colab, Python.
Research Assistant - Escuela Politecnica Nacional
July 2020 - February 2022
  • Developing simulations on C++ with GEANT4 for radiation transport experiments.
  • Data analysis and data visualization radioactive particle tracking systems.
  • Tools used: Numpy, Pandas, Matplotlib, Seaborn, Linux, Terminal, Online servers, Python.
Intern - Escuela Politecnica Nacional
October 2019 - June 2020
  • Data analysis, data treatment and data visualization of data from radiation detectors.
  • Developing modules to simplify radiation detector calibration with Python.
  • Tools used: Numpy, Pandas, Matplotlib, Seaborn.

Academic Competences

Scientific Papers

SAS GEANT4 application and machine learning algorithms for radioactive particle tracking
  • Journal: Radiation Physics and Chemistry
  • Status: Published.
e-RPT: Ecuadorian Radioactive Particle Tracking. Proposal and Evaluation of a low-budget RPT system with GEANT4
  • Journal: Applied Radiation and Isotopes
  • Status: Published.
Simulation of a HPGe Detector with GEANT4
  • Journal: Revista Politécnica
  • Status: Published
  • August - 2022

Extracurricular Activities

Vice-presidentTheoretical Physics Club

August 2021 - May 2022

Escuela Politécnica Nacional

Academic Vice-presidentChemical Engineering Students Association

February 2020 - May 2021

Escuela Politécnica Nacional

Sebastián

Sarasti

Follow me on my social media channels to know more about my projects.

Follow Us

Get In Touch

Pujilí, Cotopaxi, Ecuador

sebitas.alejo@hotmail.com

© Sebastián Sarasti Zambonino. All Rights Reserved.

Designed by HTML Codex

Edited by Sebastián Sarasti and Angel Bastidas