I am a contract data scientist, bioinformatician and software developer with experience of a broad range of languages, but primarily Python and SQL. I have a 1.1 degree in Computer Science and subsequently completed a Ph.D. in Computational Genetics, in addition to over ten years industry experience in the management consulting, IT and finance sectors. I am organizer of the Cork Big Data & Analytics group (www.meetup.com/Cork-Big-Data-Analytics-Group) which hosts regular presentations on data science topics and now numbers over 1100 members.Skills summary:1. Software development and data wrangling• 10 years professional and 7 years academic software development experience.• Particularly experienced with Python (pandas/NumPy/SciPy etc.) and SQL but also Java, Perl, JavaScript, HTML, C and VB, primarily in a Linux server environment.• Aggregation, cleaning, loading and transformation of enormous datasets for statistical and predictive modelling using a variety of RDBMS (Oracle, PostgreSQL, SQL Server, MySQL).2. Statistical Big Data analysis• Application of a range of statistical techniques, particularly machine learning methods, primarily using scikit-learn (Python) and also MLlib (Apache Spark) to minimise latency.• Cross-validation of results and detection of overfitting to avoid selection of models with an inability to generalize.• Familiar with several statistical software packages including R, SAS and SPSS.3. Communication and team management• Management of projects through the entire lifecycle using an iterative and agile methodology.• Communication of results in a format appropriate for the intended audience, including in peer-reviewed scientific journals.• Mentoring, feedback and continuous improvement of team members based on performance reviews.