Data Scientist I

About Pivot Bio: 

Fueled by an innovative drive and a deep understanding of the soil microbiome, Pivot Bio is pioneering game-changing advances in agriculture. Our first commercial product harnesses the power of naturally-occurring microbes to provide nutrients to crops.  We are dedicated to providing new sustainable ways for farmers to improve yield as they work to help feed the world’s growing population. Read/Hear more about Pivot Bio on Forbes or PBS News Hour.

Position:  Data Scientist I. Location: Pivot Bio headquarters in Berkeley, CA. Remote okay.

Pivot is rapidly expanding R&D teams that contribute to the development pipeline from early research to pre-commercialization. Along with this expansion comes an increase in the experimentation and data produced. We seek a Data Scientist to be a critical member of this growing team. This person will be responsible for holistic support, from aiding with design of experiments (DOE) and power analyses to building and implementing tools for fast and quantitative analysis of data produced from experimentation. The preferred candidate will have experience working with high-throughput data and be able to improve data driven decision making by using proper statistical design and analysis that enables the team to address pertinent questions within each experiment. 

Responsibilities:

• Partner with R&D groups to design statistically-sound experiments, including running of power analyses
• Statistically analyze diverse data sets (large, small, robust, sparse, etc.) to provide insight on research questions and drive data-based decision making
• Build predictive models to aid product decisions and reduce running of expensive and time-consuming assays
• Aid in designing, building, and testing pipelines / tools to standardize power analyses, visualizations, and statistical analyses within and across R&D groups
• Mentor and empower lab groups to implement proper statistical design and analyses for the research questions being aske

Required Skills and Experience:

• PhD in cell biology, microbiology, ecology or a related field with biostatistical experience or PhD in statistics, math, or other quantitative discipline with biological experience.
• 3+ years of relevant experience in experimental design and data analysis
• Experience extracting meaningful insights from real-world biological data to guide experimental design, scale translation and predictive modeling.
• Experience building intuitive visualizations for non-data scientists
• Strong experience in statistics, including Bayesian inference, hierarchical modeling, and analysis of diverse datasets  
• Verbal and written communication to explain designs/analyses to a range of stakeholders with different levels of data comfort 
• Python (preferred) / R experience for visualizations, running statistical analysis, and automating removal or correction of incorrectly formatted data
• Proficiency in Unix-like systems, git, and in documenting code.
• Comfortable using APIs and SQL to query and interact with relational databases.
• Pro-active in building relationships with R&D teams that have a range of analysis and statistical skills and needs.
• Skilled in asking clarifying questions to identify and build solutions that meet a team’s needs
• Knowledge of diazotroph biology a plus 

*Must be authorized to work in the United States 

What we offer: 

• Competitive package in a disruptive startup 
• Stock options 
• Health/Dental/Vision insurance with employer-paid premiums 
• Life, Short-Term and Long-Term Disability policies 
• Employee Assistance Program with free referrals and discounts 
• 401(k) plan, 3% Match 
• Commuter benefits 
• Annual Training & Development support 
• Flexible vacation policy with a generous holiday schedule 
• Exciting opportunity to work with a talented and fun team