Principal Scientist II - Data Science

Company Description

Syngenta Crop Protection is an innovative leader in agriculture, introducing groundbreaking technologies and solutions that enable farmers to farm both productively and sustainably. We offer a top-tier portfolio of crop protection solutions for the health of plants and soil, in addition to digital solutions that revolutionize farmers' decision-making capabilities. With our 17,900 strong employee force, we work to enhance agriculture in over 90 countries globally. Based in Basel, Switzerland, Syngenta Crop Protection is part of the wider Syngenta Group.

Follow us on Twitter at , and LinkedIn at .

Our Site:

The Jealott's Hill International Research Centre is nestled between Bracknell and Maidenhead in delightful semi-rural surroundings, currently home to approximately 800 Syngenta scientists and support staff. It is one of the major global research and development sites where activities such as research into discovery of new active ingredients, new formulation technologies, product safety, technical support of our product range, and seed research take place.

The Crop Protection Bioscience function at Syngenta contributes to the design of safe crop protection products via in-depth insights into biology, action mode, resistance mechanisms, and ADME, bolstering product performance and sustainability. We collect massive amounts of data throughout Bioscience, and our digital group uses a combination of image processing, statistical, artificial intelligence, and machine learning techniques to assist data-driven decision-making. A sizeable portion of the work involves designing complex experiments, integrating diverse data sources, and extracting knowledge. If you are passionate about devising computational solutions to help Syngenta create products that can feed the world sustainably, we have the job for you.

Job Description

Role Overview:

In the Crop Protection Bioscience department, we are seeking an ambitious, innovative individual to partner with scientists across the Crop Protection business to establish a vision of facing future challenges in crop health management using a digital-first approach. You will apply your experience in analyzing experimental scientific data to create models that yield new insights, which will further bioscience research programs. This role will focus on the development and deployment of algorithms, establishment of ETL (Extract, Transform, Load) pipelines, creation of visualizations, and communication of statistical results to a broad audience. Successful candidates will join the data science community within Syngenta and contribute to Syngenta's predictive modeling platform.

Responsibilities:

• Understand the Bioscience data landscape, key data attributes, and experimental capabilities to identify opportunities for enhancing our science via deploying analytics methods and predictive models.
• Identify data needs and provide recommendations to scientists to ensure data integrity
• Research, apply, and develop cutting-edge machine learning and data-driven strategies to tackle Crop Protection challenges
• Evaluate algorithm performance, assess model assumptions and their uncertainties, and effectively communicate findings to both technical and non-technical audiences
• Collaboratively work as part of the Bioscience Digital group and the broader data community to deliver and deploy new models, share learning, new methods, and technologies, and drive digital and data science innovation.

Qualifications

Education & Experience:

Applicants with an MSc/PhD (or equivalent experience) in natural sciences with emphasis on data analysis and integration, data science, and/or machine learning are preferred. Postdoctoral experience in life sciences research or experience in an R&D environment is desirable.

Required Skills:

• Aptitude for extracting and communicating knowledge from data
• Dynamics personality with a passion for innovation and problem-solving
• Experience in creating mathematical models and understanding of experimentally derived biological data, data types, appropriate analytical methods, and fundamental statistical concepts
• Ability to work in multi-functional teams
• Sound understanding and hands-on experience with standard R and Python data science stack, including libraries used for data cleaning, modeling, visualization, and machine learning
• Understanding of data-driven web apps and corresponding tooling, e.g. Plotly/Dash and R shiny, including deployment
• Familiarity with both relational and non-relational databases, including graph databases, and understanding of good data management practices for scientific data
• Understanding and adherence to best practices for software development within a team environment
• Basic understanding of deep learning techniques
• Proficient in both written and spoken communication skills
• Ability to manage and contribute to projects autonomously
• Experience with version control systems and creating reproducible digital workflows

Desirable Skills:

• Experience in creating mechanistic models
• Experience in designing data models and database management
• Experience in creating ADME models
• Knowledge in Cell Biology, Entomology, Phytopathology, Developmental Biology
• Experience with object-oriented programming

Additional Information

We embrace and encourage diversity, which fuels our innovation and outperforms the market. 

Did you know? Syngenta has been ranked as a  by the Science Journal