Looking for a Data Scientist to take over current solution for price prediction and Just in Time, and get current model ready for replication to other sites. Familiar with Deep Learning LSTM, Statistics,Prediction on Intervals. Knowledge of Baysian, BMA, LGM - or best algorithms for predictions up to 6 months. Future things to look at - Uncertainty model/ volatility.
Shell is a global group of energy and petrochemicals companies, with approximately 80,000 employees in more than 80 countries and territories. Shell helps to meet the world's growing demand for energy in economically, environmentally and socially responsible ways. Shell recognizes the strategic role of statistics and data science in supporting its operations and functions of its customers. The Capability Centre Data Science and Machine Learning supports all businesses in Shell with digital products including data science components. We are looking for people with the ability to translate a business question into a data science solution. Our Capability Centre is focussed on the development of Digital Products with a strong Data Science component. This requires that you have next to your knowledge of machine learning and/or statistics a good grasp of software development. Next to the data science capabilities and experiences you should be able to clearly and effectively present findings to our colleagues in other areas of expertise and business stakeholders. This role is particularly to support our Fuel Pricing team in the US with the continuous development of an existing model to optimise the pricing decisions. Next to that you will have the opportunity to also support other challenges in pricing across our Mobility (Retail) business.
• Developing data science solutions to solve business challenges.
• Write clean and maintainable production-level code, including tests; the tech stack we work with includes (you don't need to have an experience with all of them): Python, GIT, Azure, R, SQL.
• Integrating models into production on a weekly or even daily basis
• Work closely with the customer and the Product Owner day-to-day
• Work in a highly-collaborative, friendly Agile environment, participate in Ceremonies and Continuous Improvement activities.
• Documenting and explaining the results of analysis or modelling to both a technical and non-technical audience
• Learning new engineering practices, technologies and continuously improving our Agile practices
Required Skills and Experience
• MSc or equivalent in Statistics, Mathematics, Econometrics or similar discipline with at least 5 years' experience on data science projects.
• Broad experience and knowledge in Statistics, Machine Learning, Deep Learning and data engineering, for this role in particular (multivariate) time series analyses and other ML models like LSTM, gradient-boosting tree, Bayesian autoregression are of particular interest.
• Highly proficient in Python,R, familiar with python IDE tools like pycharm, VScode etc.
• Experience using Scikit learn, tensorflow, Keras, Shap, hyperparameter tuning for ML
• Awareness of issues in statistics and dependence on data quality • A practical common sense approach to problem solving and attention to detail.
• A passion for and expertise in practicing data science to solve real-world customer problems.
• Excellent oral and written communication skills.
• Strong interpersonal skills and enthusiasm for team work, as well as the ability to work independently. • High standards of code quality, making use of version control tools.
• Experience with high performance computing,linux, python job submission
• Experience with Databricks is beneficial
• Good knowledge of cloud environment like specifically Azure is required.
• Experience in Agile working methodology
• Coaching capability for more junior team members