Jose Dianes
Principal Data Scientist
Cambridge, England, United Kingdom
Summary
🤩
Rockstar🎓
Top SchoolJose Dianes is a Principal Data Scientist with 14 years of experience blending computational science, statistical modelling and machine learning to solve problems across life sciences, ambient sensing and real-time simulation. Based in Cambridge, he has worked at the intersection of academia and industry—from PhD research to senior engineering roles at EMBL-EBI and applied data science leadership at Chronomics and Mosaic Therapeutics. He brings hands-on expertise in big-data tooling (notably PySpark) and production ML—demonstrated by open-source Spark notebooks and a MovieLens recommender that bridges research and web deployment. Comfortable leading teams of varying sizes, Jose pairs technical autonomy with practical delivery, often translating complex simulations and bioinformatics challenges into reproducible analytics pipelines. A detail that sets him apart is his long arc from research engineer to principal scientist, giving him deep domain intuition alongside production engineering skills.
14 years of coding experience
15 years of employment as a software developer
Bachelor's degree, MSc, Bachelor's degree, MSc at Universidad de Málaga
Spanish, English
Stackoverflow
536reputation
30kreached
8answers
0questions
plotly
top-5%
Github Skills (30)
apache-spark10
spark10
python10
data-science10
pandas10
big-data10
machine-learning10
ipython10
exploratory-data-analysis10
eda10
ml10
data-preprocessing10
sentiment-analysis10
collaborative-filtering10
recommender-system10
Programming languages (7)
Github contributions (5)
jadianes/data-science-your-way
Jul 2015 - Apr 2021
Ways of doing Data Science Engineering and Machine Learning in R and Python
Role in this project:
Data Scientist
Data ScientistContributions:121 commits, 15 PRs, 69 pushes in 5 years 10 months
Contributions summary:Jose appears to be primarily focused on data analysis and model implementation within the repository. The commits showcase the user working on creating and preparing dataframes, likely for a data science project. The user then implemented methods for indexing and data selection, and some initial exploratory data analysis tasks. The user also worked on a Python script for a sentiment analysis and also started a Django app.
engineering-sciencedata-analysispythonsciencehypothesis-testing
jadianes/spark-movie-lens
Jul 2015 - Apr 2017
An on-line movie recommender using Spark, Python Flask, and the MovieLens dataset
Role in this project:Data Scientist / ML Engineer
Data Scientist / ML EngineerContributions:41 commits, 9 PRs, 19 pushes in 1 year 9 months
Contributions summary:Jose's commits primarily focus on building a movie recommender system using collaborative filtering techniques within a Jupyter Notebook environment. They started with the initial setup, and then progressed to loading, parsing, and preprocessing the MovieLens dataset to prepare the data for training. The user then implemented the Alternating Least Squares (ALS) algorithm using Spark MLlib to train the collaborative filtering model. Finally the user demonstrated how to evaluate the model using RMSE, how to make recommendations, and how to integrate with a Flask web-service.
pythonrecommendermovie-recommenderon-linemovielens
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.