Ginkgo Bioworks

Our mission is to make biology easier to engineer.

Senior Data Scientist at Ginkgo Bioworks

Location
Boston, MA or Remote / Remote
Job Type
Full-time
Experience
6+ years
Apply to Ginkgo Bioworks and hundreds of other fast-growing YC startups with a single profile.
Apply to role ›

About the role

Ginkgo is constructing, editing, and redesigning microorganisms to answer humanity's most pressing challenges in health, energy, food, materials, and more. Our mission is clear--to make biology easier to engineer--and it is the foundation of everything we do at Ginkgo. On the Data Team, our focus is the strategic application of data science and engineering across our business. We tackle diverse problems that span molecular biology, robotic automation, finance & business strategy, and operations, all in service of supporting data-driven decision-making. We do that through a combination of durable software tools, closely embedded analysts, and side-by-side collaboration with data engineering. This role will be primarily focused on analytical automation and support for high-throughput screening, i.e. automated outlier detection, normalization for batch effects, and hit detection, and delivery of results in clean, easy-to-understand outputs.

As a Data Scientist, you’ll join a highly collaborative team composed of data engineers, analysts, and data scientists with a wide range of backgrounds and experiences. You'll partner closely with scientific collaborators from across Ginkgo to develop analysis plans, build durable reports, on-board and train partners, and work with data analysts and engineers to deliver data-driven software tools. Ideal candidates are self-starters and strong technical contributors who can identify opportunities to solve problems with data. Candidates should be curious and eager to learn about both the science and the business, possess analytical skills to uncover rich insights from complex datasets, and excel at communicating your work to audiences with varying degrees of technical expertise.

Every day we face new technical and scientific challenges that require deep cross-functional collaboration and novel solutions. Success in this evolving field is only possible with teams that represent diverse people, ideas, backgrounds, experiences, and ways of working. Active inclusion is core to how Ginkgo wins. We’re an equal opportunity employer and encourage individuals from underrepresented backgrounds to apply.

Technical excellence

  • Experience working with biological data, specifically in the context of high-throughput screening is a plus.
  • Track record of delivering end-to-end data science products, i.e. ability to work across the product lifecycle from exploration and discovery, to operationalization and production.
  • Experience analyzing complex data, drawing conclusions, and making actionable recommendations.
  • Strong project management skills including managing complexity and making informed trade-offs to quickly escape rabbit holes and make on-time deliveries. Experience with Agile workflow practices and familiarity with Atlassian tools including Jira, and Confluence is a plus.
  • Fluency and practical experience with statistical methods like exploratory data analysis, hypothesis testing, power analysis, regression, and generalized linear models, as well as familiarity with advanced methods like, time-series and survival analysis.
  • Fluency and practical experience with machine learning concepts and algorithms in supervised and unsupervised learning settings. Examples include general machine learning workflow, linear/logistic regression, decision trees, neural networks, clustering, etc.
  • Fluency and practical experience with data visualization techniques and best practices, and deep skill in at least one visualization tool.
  • Software development best practices including story estimation, test-driven development, code review, and version control with git.
  • Deep Python skills including familiarity with pandas, scikit-learn, and advanced visualization libraries such as Altair, seaborn and matplotlib is preferred.
  • Extensive experience with SQL required. Experience working with NoSQL data environments and tools such as Hadoop, Spark, DynamoDB is a plus.
  • Experience writing and maintaining ETL workflows with tools like Airflow or Luigi is preferred.
  • Experience with the Amazon Web Services ecosystem is a plus.

Relationships and communication

  • Excellent written and verbal communication skills are required.
  • Aptitude for breaking down complex technical and quantitative topics for audiences with mixed levels of technical expertise. In particular, translating technical and scientific concepts into business outcomes and recommendations is essential for success in this role.
  • Comfort and aptitude for presenting work progress, insights, and recommendations to stakeholders and senior leadership.
  • Willingness to work on a distributed team and adhere to common working hours across time zones. Familiarity with communication strategies and tactics for distributed teams is a plus.
  • Strong technical writer and documenter.
  • Track record of storytelling with data, specifically supporting data-driven decisions with compelling visualizations using tools like Tableau, seaborn / Altair, and/or ggplot2 / shiny.

Why you should join Ginkgo Bioworks

Ginkgo Bioworks is the organism company. We design custom organisms for customers across multiple markets. We build our foundries to scale the process of organism engineering using software and hardware automation. Organism engineers at Ginkgo learn from nature to develop new organisms that replace technology with biology.

Engineering biology isn't easy. It is frustratingly, painfully difficult. It's programming without a debugger, manufacturing without CAD, and construction without cranes. At Ginkgo we are building a team that can build debuggers, write CAD, and operate cranes. We are looking for the best engineers, scientists, and hackers.