Field Data Scientist
Indigo is a company dedicated to harnessing nature to help farmers sustainably feed the planet. With a vision of creating a world where farming is an economically desirable and accessible profession, Indigo works alongside its growers to apply natural approaches, conserve resources for future generations, and grow healthy food for all. Utilizing beneficial plant microbes to improve crop health and productivity, Indigo’s portfolio is focused on cotton, wheat, barley, corn, soybeans, and rice. The company, founded by Flagship Pioneering, is headquartered in Boston, MA, with additional offices in Memphis, TN, Research Triangle Park, NC, Sydney, Australia, Buenos Aires, Argentina, and São Paulo, Brazil. www.indigoag.com
- Develop a comprehensive understanding of Indigo's data structures and metrics.
- Perform end-to-end analysis including collection of data, development of data specification requirements, data processing and normalization, and statistical modeling on an ongoing basis and on challenging deadlines.
- Design and develop visuals of datasets and modeling results and present these as compelling storyboards to non-technical audiences.
- Contribute to thoughtful business and sales recommendations using effective presentations of findings through synthesis and visualization of quantitative information.
- Be extremely comfortable working with messy agricultural and biological datasets from a variety of non-normalized sources and imbued with high level of ambiguity.
- Interact effectively with a very diverse set of teams including, but not limited to agronomy, engineering, sales, logistics, operations research, product development and project management.
- Be able to lead a team with self-direction. Be able to both teach and mentor teammates and learn new techniques.
- Be able to work on complex analysis problems, identify and apply appropriate advanced statistical analysis techniques as necessary.
- Be comfortable with drawing conclusions from ambiguous data and recommend future course of actions.
- PhD degree in a quantitative discipline (e.g. statistics, biostatistics, epidemiology, applied mathematics, or similar) or equivalent practical experience.
- 2-3 years of industry experience in statistical sampling and resampling methods, and modeling techniques such as multivariable modeling and/or machine learning techniques.
- Advanced programming experience in a statistical language. R or Python is preferred. Working experience with a wide range of statistical, geospatial and machine-learning libraries in R or Python is a plus.
- Experience with databases (SQL/Postgres) and scripting languages (such as Python, Shell).
- Familiarity with linux/unix and high-performance computing environments such as AWS and Google Cloud Compute.