• Identification and prioritisation for projects in a dynamic environment, with a keen eye for where ‘maximum value’ can be delivered.
• Applying machine learning models / optimization in creative ways to heterogeneous data sets.
• Taking concepts from POC into production
• Always seeking new ways, us utilising data and modelling into the day-to-day inner workings of the commodities industry.
• MSc or PhD level Computer Science, Machine Learning, Applied Statistics, Mathematics.
• 3-5 years of hands-on experience in applying data science methods to real-world business problems.
• Experience of getting the best results from messy data sets
• Python (3), high level of capability in writing understandable / extensible /well-documented code.
• Experience of data storage platforms (SQL, NoSQL, Map-Reduce frameworks, etc.)
• Attention to detail / thirst for real answers from data (how, why, what, when)
• Experience presenting data visually (Plotly, D3, Tableau).
• Time series modelling (ML / econometrics)
• Enterprise software development (code design, review, gitflow, etc.)
• Cloud-based data science workflows (on AWS in particular)
• Deep Learning (able to translate deep learning models).
• Self-Motivation / discipline
• 'People first' / natural collaboration skills
• Methodical / rigorous / daring
• Able to work independently and in teams and with all levels of an organisation
• Team player / unpolitical working style
• The desire to be a thought-leader / partner and make a serious impact on the bottom line of the company (energy flows)