Client: coreva Location: remote Duration: 1 year+ Rate: open Description: Corteva Agriscience™ has an exciting opportunity for a Data Science Contractor. The successful candidate will join a strong, globally distributed Data Science team that develops and applies innovative methods and tools to deliver insights for Corteva R&D. The candidate will partner with leading toxicologists, environmental scientists, and discovery scientists to support our growing data science effects in predictive safety. The candidate must have experience and fundamental knowledge in machine learning and/or statistics as well as programming skills to develop and deliver novel data science solutions in an industry setting. Responsibilities:
- Partner with scientists to develop, prototype, and deliver rigorous machine learning and statistical solutions aligned to project needs
- Pre-process high-complexity datasets such as high-throughput bioassays
- Communicate and train research partners on data science models and products to facilitate data-driven decisions
- Partner with engineering and production teams to deploy data products at scale
- Communicate insights derived from complex data analysis into simple conclusions that empower leadership to drive action; communicate results in internal and external forums; and contribute to scientific articles as needed
- Steward data product life cycle and partner with other data scientists to continuously improve underlying models
Educational Qualifications M.S + 3 years' experience or Ph.D. degree in Statistics, Applied Statistics, Biostatistics, Computer Science, Data Science, Engineering, Physics, or related highly quantitative fields. Additional years of experience preferred but not required. Required Qualifications
- Expertise in R or Python programming for data wrangling, statistical analysis, and machine learning applications
- Fundamental understanding of machine learning techniques for classification (e.g., logistic regression, random forest, XGBoost, SVMs, K-means, neural networks)
- Fundamental knowledge of statistics
- Understanding of dimensionality reduction; model diagnostics; and model training, testing, and validation
- Ability work both independently and within a multidisciplinary team environment
- Ability to successfully collaborate with colleagues from diverse technical backgrounds which includes excellent communication, interpersonal, verbal, and written skills
- Strong critical thinking and problem-solving skills, flexibility, and willingness to learn
Preferred Qualifications:
- Experience with visualization and rapid prototyping tools (e.g., R Shiny, Python Dash, R plumber)
- Experience developing in an agile team environment using modern DevOps tools (e.g., Git, Docker)
- Familiarity with modeling biological, cellular, or ecological data
- Familiarity with molecular biology or biochemistry concepts
- Familiarity with data science in Agriculture