I am a Software Engineer working since 2010 at the European Bioinformatics Institute, having previously spent over 8 years as a university researcher in the field of Machine Learning and Bioinformatics, giving me a good blend of enterprise and academic experience.

I enjoy contributing to the creation of great products for the benefit of people and working in a dynamic environment with a focus on good development practices and automation.

When not working, I enjoy playing with my wonderful two children, writing poetry and thinking outside of the box.

Machine Learning   Data Science   Data Mining   Bioinformatics   C++   Python   R   Perl   REST   SQL   MySQL   Elasticsearch   Design Patterns   Test-driven Development   Continuous Integration  

Title	Start Date	End Date	Company	Role
Software Engineer	2013	Ongoing	European Bioinformatics Institute	I work as a software engineer for Ensembl, where I collaboratively develop and maintain the core/REST APIs and various data intensive pipelines used in the release cycle. I have developed and currently maintain the Trackhub Registry, a global, centralised collection of publicly accessible track hubs published by researchers worldwide and directly loadable into popular genome browsers. As part of my work, I co-develop and maintain Bio::DB::HTS, a popular Perl interface to the the HTSlib library to access high-throughput sequencing data . I am also lecturing at the Ensembl API workshops at the European Bioinformatics Institute and the University of Cambridge and give presentations about our work around the UK.
Project Manager	2016	2017	European Bioinformatics Institute	I have supervised the migration of the hardware and software infrastructure of the Ensembl team from the Sanger Institute to the European Bioinformatics Institute
Data Scientist	2012	2013	Self employed	Project "Pheasant", funded by the regional government of Tuscany (Italy). I run statistical analyses and Machine Learning based predictive modeling using biometric data from samples of pheasants in the ZRC ATC 19 governmental game reserve.
Bioinformatics Engineer	2010	2013	European Bioinformatics Institute	I was the lead software developer of Microme, a EU-funded project involving several institutes in Europe to develop a large scale infrastructure for the storage and processing of computational models of microbial species.
Freelance Web Developer	2008	2010	Self employed	I designed, implemented and maintained various commercial web sites.
Research Associate	2007	2009	Complex and Adaptive Systems Lab, University College Dublin	I researched and developed Machine Learning models for protein disorder prediction and cheminformatics. I have also applied machine learning techniques to study protein pseudo-folding pathways.
Post-doctoral fellow	2004	2007	School of Computer Science and Informatics, University College Dublin	Design and implementaton of Machine Learning models to automatically interpret and annotate molecular biology data on a very large scale. I have developed the interface, server-side scripts and main application of various tools and servers for protein structure/disorder prediction (Distill). I was also responsible for the set up and administration of the computational cluster of the AmMBIO group.
Visiting Researcher	May 2003	Sep 2003	University of California at Irvine	In partnership with the School of Information and Computer Sciences and the Institute for Genomics and Bioinformatics to further explore the potential of new deterministic graphical models based on Recursive Neural Networks in protein structure prediction problems.
Co-Director, Full-stack Web Developer, Linux System Administrator	1997	2001	NewNet Informatics Ltd	I founded a small start up together with friends and colleagues from university. The company worked as an Internet Service Provider and provided customised web applications and e-commerce solutions based on PHP and Javascript.
Post graduate Researcher	1999	2000	Department of Systems and Computer Science, University of Florence (Italy)	Project META-E The Metadata Engine Project, IST Programme, Area "Digital heritage and cultural content", EU Grant IST-1999-20021. Model design and development of probabilistic graphical models for document classification (text categorization). I have employed the C++ framework developed during my master thesis to train and test HMMs to capture the sequential structure of certain document spaces, and modeling the emission distribution with either Naive Bayes or Hidden Tree Markov models (HTMMs).

Certification	Subject	Date Completed	University
Doctor of Philosophy (Ph.D)	Machine Learning and Bioinformatics	2004	Department of Systems and Computer Science, University of Florence (Italy)
Master of Science (M.Sc.)	Computer Engineering	2000	University of Florence (Italy)