X

Contact Me

Email: castajhon@gmail.com


John Castaneda

About Me

As a Data Scientist, I apply advanced analytics, machine learning, and optimization techniques to solve complex problems and drive measurable impact. With nearly a decade of combined industry and academic experience in Operations Research including three Q1 journal publications that demonstrate my problem-solving depth. I specialize in building scalable, data-driven solutions that enhance decision-making and operational performance. I work with Spark and the Azure ecosystem, leveraging distributed computing and cloud-native workflows to build robust data pipelines, deploy models at scale, and orchestrate end-to-end analytics solutions. Beyond modeling, I also develop complete analytics products, combining both back-end engineering (APIs, pipelines, model deployment, orchestration) and front-end capabilities (dashboards, interactive applications, and user-facing tools) to deliver solutions that are fully functional and easy for stakeholders to use.


Research Interests - Keywords

Data Science, Machine Learning, Deep Learning, Python, large language models, mathematical modeling, Transport optimization models.

Skills

Programming & Tools

  • Python
  • SQL
  • JavaScript
  • C++
  • Matlab
  • Git
  • Docker
  • React.js
  • Pandas
  • NumPy
  • LaTeX
  • Microsoft Office

Data Science & AI

  • Data Science
  • Machine Learning
  • Deep Learning
  • Neural Networks and Deep Learning
  • Large Language Models (LLM)
  • Artificial Intelligence (AI)
  • AI Agents
  • Algorithm Development
  • Computer Science
  • Software Development
  • PySpark

Cloud & DevOps

  • Microsoft Azure
  • Azure Data Factory
  • Azure Databricks
  • DevOps

Analytics & Visualization

  • Data Analytics
  • Data Visualization
  • Microsoft Power BI
  • Time Series Analysis
  • Hypothesis Testing

Research & Optimization

  • Operations Research
  • Optimization
  • Metaheuristics
  • Mixed-Integer Linear Programming
  • Research Proposals
  • Algorithms

Other Skills

  • Robotic Process Automation (RPA)
  • Data Quality
  • Problem Solving
  • Power System Operations
  • Engineering
  • Energy
  • Electrical Engineering
  • Team Leadership

Work Experience

My most impactful career experience was at a power distribution utility, where I successfully transitioned from an Electrical Engineer to a Data Scientist. By combining my foundational engineering knowledge with advanced analytics, I helped optimize complex operations within the energy sector. Bridging the gap between physical energy systems and data-driven solutions has given me a highly analytical, unique perspective to bring to any technical team. Below is a summary of my recent roles:


Sr. Data Scientist

Avnet


Oct 2025 - Present

• Developed AI-powered applications to extract data from technical manuals.

• Analyzed captured data to unify existing business information using embeddings.

• Led project development leveraging the Databricks platform.

Data Analytics Team Coordinator

CHEC Grupo ΕΡΜ


Feb 2024 - Oct 2025

• Develop a roadmap for the Data Analytics team to implement use cases related to publishing dashboards and web data applications, leveraging operational information for decision-making and system optimization.

• Lead a project focused on optimizing the scheduling and allocation of resources to handle failures such as corrective and preventive maintenance in the power distribution system.

• Develop Robotic Process Automation (RPA) solutions to streamline corporate processes. • Direct and develop initiatives in Generative Artificial Intelligence using LLMs to optimize resources, enhance support for internal and external clients, and standardize and improve information flow in corporate areas.

• Implement AI agents to automate decision-making and coordination tasks, improving the efficiency and responsiveness of corporate processes such as customer service, logistics, and internal operations.

• Develop data-driven applications and conducted in-depth analyses of operational information. These initiatives improved efficiency, optimization, and overall management of the electrical distribution system.

Researcher - Optimization of transport systems

UNIVERSIDAD TECNOLÓGICA DE PEREIRA


Aug 2018 - Oct 2025

• Researcher in Operations Research (Vehicle Routing Problem - VRP).

• Professor (Operations Research)

• Python for Data Science (2025)

• Metaheuristics (2024)

• Research Seminar (2023)

Introductory MATLAB (2022)

• Algebra and Differential-Integral Calculus (2016)

Sr. Engineer

CHEC Grupo ΕΡΜ


Dec 2016 - Feb 2024

• Developed data-driven applications and conducted in-depth analyses of operational information. These initiatives improved efficiency, optimization, and overall management of the electrical distribution system.

• Collaborated in the development and formulation of projects related to user consumption analysis, diversified demand definition, and demand curves for distribution transformers, using statistical techniques, regression models, and clustering methods based on user categories.

• Contributed to the development of the "distribution system analysis and planning" project by building a machine learning model for imputing missing data captured in the SCADA system, enabling the simulation of lost data for load flow simulation models.

• Developed and implemented dashboards for monitoring distribution system operation KPIs, using technologies such as Power BI and Python.

Education

Over the past few years, I have focused my career on Data Science and Transport Optimization. I have earned two master's degrees in these fields and I am currently pursuing a PhD. My academic and professional experiences have provided me with a strong foundation in data analysis, mathematical modeling, and optimization techniques, which I have applied to real-world problems in transportation and logistics. I am passionate about leveraging data and technology to drive innovation and improve efficiency in the industry.


PhD in Engineering

Universidad Tecnológica de Pereira - Colombia


Aug 2020

Master of Science - MS, Electrical Engineering, Grade: Laureate Thesis

Universidad Tecnológica de Pereira - Colombia


2017 - 2021

Master of Science - MS, Operations Research and Statistics

Universidad Tecnológica de Pereira - Colombia


2014 - 2018

Bachelor’s degree, Electrical Engineering

Universidad Tecnológica De Pereira - Colombia


2003 - 2009

Data Science For All / Colombia 5.0: Graduated with Honors

Correlation One


2021

Credential ID 39156730

Certifications and Courses

Additional certifications and courses completed:

Publications and Proyects

Two-echelon vehicle routing problem with integrated drones and unmanned ground vehicles International Journal of Management Science and Engineering Management. Apr 15, 2025

Iterated local search multi-objective methodology for the green vehicle routing problem considering workload equity with a private fleet and a common carrier. International Journal of Industrial Engineering Computations, 12(1), 115-130.

Iterated local search for the vehicle routing problem with a private fleet and a common carrier. Engineering Optimization, 52(10), 1796-1813.