In Bayer’s Crop Science division, we shape agriculture through breakthrough innovation that helps to nourish our growing world, preserve natural resources and deliver better solutions for all farmers. Using the creative spark that comes from human ingenuity, we seek to deliver world-class innovation, set new standards in sustainability, and drive our digital transformation. Our products include high-performance seeds & traits, crop protection solutions, and digital farming tools.

YOUR TASKS AND RESPONSIBILITIES

The primary responsibilities of this role, Data Scientist Co-op, are to: 

• Work closely with his/her mentor to help develop the capability to simulate a digital twin of all of our breeding decisions connected together;
• Develop the algorithms needed to extract actionable insights from that twin in order to help drive the pipeline more efficiently to the most desired outcome;
• Be tasked with exploring cutting edge technologies including as Long-Short Term Memory Recurrent Neural Networks and Generative Adversarial Networks among others in the context of how they may be applied to explore possibilities and identifying optimal advancement strategies within a digital twin of our breeding pipeline;
• Demonstrate the value of the simulations and analytics described above by applying them to data from past years in a specific breeding pipeline;
• Work with his/her mentor to demonstrate the value of the simulations and analytics described above by applying them to real, valuable decisions within a specific breeding pipeline;
• Build and validate predictive models incorporating key breeding data including but not limited to environmental, operational capacity and genomic data as necessary to support the above objectives;
• Deliver a working demonstration of adjusting breeding targets within a connected part of a breeding pipeline using validated machine learning methodologies.

WHO YOU ARE

Your success will be driven by your demonstration of our LIFE values.  More specifically related to this position, Bayer seeks an incumbent who possesses the following:

Required Qualifications:

• Currently enrolled in a Master of Science/Ph.D. in Computer Science, Statistics, Data Science, Mathematics, Computational Biology or other Quantitative program;
• Proficiency in Machine Learning and Statistics algorithms and concepts (Mixed Models, Random Forest, Deep Learning, SVM, etc.);
• Strong programming skills in Python, R, SQL, Java or Linux with a preference for Python;
• Experience with cloud computing platforms (AWS, GCP) and tools such as Hadoop and Spark;
• Problem solving ability and experience in analyzing and presenting complex data;
• Organizational, interpersonal and written communication skills;
• Strong business aptitude, the ability to rapidly learn new problem domains and become conversant in the domain with subject matter experts;
• Ability to communicate complex ideas in a clear, precise and actionable manner;
• Detail and results oriented with the ability to work independently;
• Ability to actively engage with internal partners and external collaborators to align strategies and success measures in analytics.

Preferred Qualifications:

• Willingness to extend own data science and statistical interests to agriculture and/or experience working with agricultural/biological scientific data;
• Experience with cutting edge ML algorithms including Long-Short Term Memory Recurrent Neural Networks and Generative Adversarial Networks.