Rubén Gijón Cañete

Data Scientist

EY • December 2022 — September 2023

I worked with a small team on the development of a classification model based on NLP (Python) with the aim of assigning a tax code to a product. We industrialized the solution using Azure Data Factory. Overall accuracy of the model 83%.

Development of an ELT process in Snowflake using pySpark, SQL, and Stored Procedres. Achieved full automation of the entire process, from new data arrival in Azure Blob Storage to the gold layer in SnowFlake.

Trainee Data Engineer

Cívica Software • March 2022 — August 2022

I received training on SQL, dbt, data engineering, pySpark and business.

I worked on developing a battery of SQL tests to validate financial data. Part of the work involved optimizing existing queries, and in some tests, we achieved a 70% improvement in performance.

Tutor

Freelance • 2013 — 2022

Private lessons in mathematics and physics from middle school to college. This work has taught me to explain hard concepts simpler as possible.

University of the Basque Country (UPV/EHU)

Master's degree in Natural Language Processing • 2023 — 2024

• Expected Skills Linguistics, Semantics, Deep Learning, Transformers, Speech recognition, NLTK...

University of Granada (UGR)

Bachelor's degree in Physics • 2017 — 2022

• Most relevant subjects Data Structures and Algorithms, Linear Algebra, Calculus, Statistics, High-Performance Computing, and Computational Physics.
• Experience in physics lab (writing papers, and statistical tests).
• Programming Skills Python (3 years), Matlab (2 years), C++ (2 years).

PoliticalPass

Deep learning project • Jupyter Notebook

My first DL proyect, consist of a neural network that predicts if a twitter account is left-wing or right-wing based on the last 100 tweets. [IN PROGRESS].

FilmAffinity's lists platforms

Web Scraping project • Jupyter Notebook

FilmAffinity doesn't show in what platforms you can watch movies from a list. Using python and BeautifulSoup4 I have implemented a solution for this problem.

Digit recognition with Neural Networks

Deep learning project • Jupyter Notebook

First deep learning project made by my own way. I implemented a CNN. I used MNIST DataSet.

Solving Zebra Puzzle with python

Leisure project • python

When I knew about Zebra Puzzle I immediately thought in programming a solution for this problem. It has been solved by the "smart way" not by trial and error. The program obtains a solution in 9 iterations (time of execution on my laptop - 0.00085 secs) .

English

Intermediate level. I'm currently preparing Cambridge's B2 exam by my own.

Python

I feel confident working with basic data structures, OOP, functional programming, numpy, pandas, pip and jupyter notebooks.

SQL

Advanced level using SQL for queries.

Maths

Advanced knowledge on maths (algebra, calculus and stadistics). I'm good solving hard problems.

Physics

Advanced knowledge on physics.

Machine Learning & Deep Learning

I have worked mostly with Scikit-learn, TensorFlow and keras.

Team worker

I would describe myself as creative, assertive and open minded.

Linux enthusiast

I'm familiar with linux environment and linux console. Pop! OS user.