Data Scientist

at  Gs Group

DATA SCIENTIST

Our company is an incredibly exciting place to work, at the forefront of modern farming and food production, G’s is one of the largest fresh produce providers in the UK, producing over one billion packs of healthy products a year.
We have an exciting opportunity for a Data Scientist to join our Innovation team, who will be working with our growers to develop models to describe how crops are growing. Through this role, you will make a significant contribution to improve our farming processes, and ultimately help deliver affordable food to the end consumer.
You will join a fantastic team which is keen to help, support and get the best out of you.

CANDIDATE REQUIREMENTS:

• Minimum 2 years’ experience in statistical modelling, machine learning and time series forecasting, particularly applied to modelling of crop maturity and growth
• Experience using standard data engineering tools, including SQL.
• Experience using standard data science development tools, including Anaconda, JupyterLab, and Python programming.
• Experience on models maintenance and ML Ops
• Excellent time management and ability to use your own initiative.
• Excellent verbal and written communication skills.
  Hours of Work: Monday – Friday - 40 hrs/week

• Develop quantitative and qualitative models to describe how crops are growing in the field.
• Use genetic algorithms to perform feature selection and identify key parameters.
• Create the basis of a digital twin for salad crops using time series forecasting and mechanistic models and articulate these in ways growers can better understand how their management affects crop result.
• Define alert systems for growers to pro-actively manage the crops.
• Propose ways of improving accuracy and further develop current models.
• Evaluate quality factors related to crop maturity.
• Assess the effectiveness of data sources and data-gathering techniques and improve data collection methods.
• Encourage G’s Growers to make smarter decisions by creating customised implementations of current models by crop and, when necessary, by crop variety.