Corteva Agriscience is a publicly traded, global pure-play agriculture company that provides farmers around the world with the most complete portfolio in the industry - including a balanced and diverse mix of seed, crop protection, and digital solutions focused on maximizing productivity to enhance yield and profitability. In 2021, Corteva Agriscience generated revenues valued at around 15.66 billion U.S. dollars.
At Corteva Agriscience, you will help us grow what’s next. No matter your role, you will be part of a team that is building the future of agriculture – leading breakthroughs in the innovation and application of science and technology that will better the lives of people all over the world and fuel the progress of humankind.
We are seeking an innovative, collaborative, and enthusiastic data scientist with computational biology expertise. The successful candidate will join a strong, global data science team that delivers value across Corteva. The position will partner with data science teammates and collaborators in other domains to shape and deliver innovative analytics and machine learning solutions for genomics, protein, and chemistry applications. These applications will have direct impacts on the discovery and improvement of Corteva’s new crop protection chemical and biological products.
The preferred location for this position is in Indianapolis, IN, USA. 100% remote is also an option for strong candidates.
• Drive innovation and value by combining state-of-the-art analytics, data integration, and biological domain knowledge
• Partner with data science teammates and collaborators across domains to understand research needs and deliver on high-impact projects
• Develop advanced analytics, including machine learning/deep learning, with applications to genomics, protein function, and chemical structures
• As driven by project needs, build and sustain a technical network (internally and externally) that is leveraged to ensure project success
• Ph.D. in Computational Biology, Bioinformatics, Computational Chemistry, Data Science, Computer Science, Statistics, or related fields with 0-5 years of experience (or M.S. with 6-10 years of equivalent experience)
• Strong computational background and experience in design and development of computational methods, algorithms, and tools for biological applications
• Experience working with –omics data and managing and dissecting large unstructured datasets (for example, protein and DNA sequences and chemical structures)
• Proficiency in machine learning and broad understanding of emerging machine learning and deep learning approaches such as transformers, generative models, autoencoders, and reinforcement learning; Practical experience with transformer architectures is a strong plus
• Practical experience in structure-based protein/enzyme design and engineering is a strong plus
• Strong Python data science skills (Jupyter, Pandas, NumPy, Matplotlib, Scikit-Learn)
• Proficiency in a Linux environment and familiarity with tools for data engineering, workflows, and software development such as Git and Docker
• Knowledge of statistical methods such as principal component analysis, linear regression, non-linear models, and experimental design
• Strong desire to learn and is a fast learner, critical thinking, a can-do attitude, strong problem-solving skills, and agility to adapt approaches to new data and information
• Excellent communication (verbal and written) skills and is a team player
• Ability to work independently and manage timelines in collaborative projects
• Experience in SQL or NoSQL database management and queries
• Practical cloud computing experience with Kubernetes
• Experience in creating web-based tools and visualization applications with Plotly Dash, R-Shiny, or D3.js
• Basic knowledge of microbiology
• Working knowledge of cheminformatics