Massachusetts Green Jobs

MassHire JobQuest Logo

Job Information

Indigo Data Scientist/Bayesian Statistician in Boston, Massachusetts

Apply NowData Scientist/Bayesian Statisticianat Indigo(View all jobs)

Boston, MA

What if nature could be harnessed to help farmers sustainably feed the planet? Since 2014, Indigo has questioned agriculture's full value chain to improve grower profitability, environmental sustainability, and consumer health. The company’s scientific discoveries and digital innovations have amplified new value from soil to sale, benefiting more than 10,000 growers to date. Indigo is also the company behind The Terraton Initiative, a global effort to drawdown one trillion tons of atmospheric carbon dioxide by unlocking the potential of agricultural soils. In 2019, Indigo was ranked #1 on CNBC’s Disruptor 50 list. Headquartered in Boston, MA, Indigo has additional offices in Memphis, TN; Research Triangle Park, NC; Sydney, Buenos Aires, Argentina; Basel, Switzerland; and São Paulo, Brazil.

The Portfolio and Data Insights Team is looking to hire a statistician or a data scientist with a solid statistical background to model field performance using evidence from across our product development pipeline. Our team is highly collaborative and works cross-functionally with research scientists, product managers, and the commercial team to drive our Microbial pipeline forward.

As a Data Scientist on our team, you will collaborate with diverse stakeholders across the microbial product development pipeline by turning laboratory plant assay, greenhouse, and field trial data into actionable insights that drive critical business decisions. The role entails i) designing and analyzing laboratory experiments to find the best predictors of field success, ii) ensuring the highest quality of statistical rigor in the analysis of experimental data, iii) constructing an informed prior distribution for the analysis of field data within our Bayesian modeling framework, and iv) leading the development of an evidence synthesis framework to drive product advancement decisions from diverse data sets. The ideal candidate will be comfortable working with large, heterogeneous data sets, have proven expertise in Bayesian modeling and statistical consulting, and have outstanding communication skills. This is a unique opportunity to drive statistical innovation and have a direct impact on key business decisions!

Responsibilities:

  • Learn the Microbials product development pipeline and sources of data at each stage

  • Gain familiarity with Indigo's data structures, analytical tools and metrics

  • Gain familiarity with existing pipelines and coding practices in the Data Science team

  • Understand the projects that other team members are working on

  • Get an overall picture of the microbial product pipeline and identify key stakeholders

  • Hold 1:1s with each sub-team and individual members of the PDI team

  • Assist with the Bayesian analyses of complex field data with particular focus on environmental interactions

  • Provide expert data science guidance to internal stakeholders on the analysis and interpretation of data

  • Contribute to existing Bayesian subfield pipeline and code repositories as needed

  • Begin scoping the construction of an informed prior based on pipeline data

  • Scope and initiate the evidence synthesis project in collaboration with data scientists and technical product manager to connect data at all stages of the R+D pipeline

  • Clearly document progress on evidence synthesis for all stakeholders, RLDT, and S&T

  • Provide statistical guidance on the analysis of experimental data and reporting of results across all stages of product development

  • Ensure rigorous documentation of changes in hit calling procedures, analyses, and data usage in the DB and on Confluence

  • Present a recommended framework for the construction of an informed prior distribution

Competencies:

  • Analysis of quantitative experimental data, especially in the biological sciences

  • Design of scientific experiments, e.g. power analyses, handling technical and biological variation, etc.

  • Experience with Bayesian modeling of data, e.g. MCMC sampling, inference, and empirical Bayes approaches

  • Experience with Python and R, and familiarity with SQL for querying databases

  • Machine learning techniques for feature selection and exploratory analyses (e.g. clustering, LDA, etc.)

  • Presenting technically sophisticated analyses to audiences at disparate levels of sophistication

  • Strong desire to continue learning, identify new techniques and technologies, and rapidly implement them to keep Indigo at the cutting edge (e.g. reading bioRxiv digests daily and testing new tools)

  • Ability to deliver in a fast-paced environment

  • Flexible and open to rapid iteration as priorities change

  • Desire to teach quantitative skills to scientists and continually increase the level of sophistication in experimental design and analysis

  • Team player, excellent communication skills

  • Passion for Indigo and our core values

Qualifications:

  • PhD in a quantitative discipline (e.g. Statistics, Biostatistics or Computational Biology) with an emphasis on statistical methods or Masters degree with 3+ years of experience

  • 2+ years of relevant industry experience

  • Experience programming in Python and R

  • Understanding of and experience working with biological data

  • Experience with spatial statistics and Bayesian modeling

  • Previous work with agriculture data is a plus, but not required

Indigo is committed to living our values, specifically “creating a work environment where everyone feels respected, connected, and has opportunities to learn and grow.” As part of living our values, we strive to create a diverse and inclusive work environment where everyone feels they can be themselves and has an equal opportunity of succeeding.

DirectEmployers