Josep Arús-pous

Principal AI ML Research Engineer & Technical Lead at Evinova

Sabadell, Catalonia, Spain
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

👤
Senior
🎓
Top School
Josep Arús-pous is an associate director of data science and machine learning with 11 years of experience building and operationalizing deep learning systems, primarily in healthtech and drug discovery. He holds a PhD in cheminformatics and has designed generative models and large-scale data pipelines to explore billion-molecule databases, bridging research-grade innovation with production engineering. At Evinova and previously at AstraZeneca and Roche he leads cross-functional teams to deliver AI-driven clinical trial and therapeutic solutions, spanning model development, data engineering, mobile apps for patient monitoring, and cloud deployment. He combines strong systems and UNIX administration roots with modern ML tooling (PyTorch, Spark, DevOps), enabling end-to-end ownership from data ingestion to scalable inference. Outside work he’s a self-described science-and-music nerd, reflecting a curiosity that drove him to build computing clusters and production platforms during his PhD. Practical, research-savvy, and product-focused, he excels at rethinking ML systems from first principles and shipping them into real-world healthcare contexts.
code11 years of coding experience
job13 years of employment as a software developer
bookPhD in Chemistry and Molecular Sciences, Computer-assisted drug discovery (Cheminformatics), PhD in Chemistry and Molecular Sciences, Computer-assisted drug discovery (Cheminformatics) at University of Bern
bookCertificate of Proficiency in English (CPE), English, Certificate of Proficiency in English (CPE), English at British Council
bookMaster’s Degree, Bioinformatics, Master’s Degree, Bioinformatics at Universitat Pompeu Fabra
bookUPC Universitat Politècnica de Catalunya
languagesEnglish, Spanish, Catalan, German
stackoverflow-logo

Stackoverflow

Stats
1reputation
0reached
0answers
0questions
github-logo-circle

Github Skills (8)

rdkit10
recurrent-neural-networks10
python10
cheminformatics10
encoder-decoder9
drug-discovery9
machine-learning8
ios4

Programming languages (3)

SwiftHTMLPython

Github contributions (5)

github-logo-circle
A SMILES-based encoder-decoder architecture for molecular scaffold decoration
Contributions:11 commits, 1 PR, 9 pushes in 1 month
encoder-decoder
undeadpixel/reinvent-gdb13

Oct 2018 - Jul 2019

A Recurrent Neural Network implementation that uses SMILES strings to generate molecules from GDB-13
Contributions:5 commits, 3 pushes in 9 months
recurrent-neural-networks
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.
Request Free Trial