Senior Data Scientist / Machine Learning Scientist

Employer
Mirvie Inc
Location
South San Francisco (partially remote can be considered)
Posted
May 20, 2022
Hotbed
Biotech Bay
Required Education
Doctorate/PHD/MD
Position Type
Full time
Mirvie is shaping the future of pregnancy health by predicting unexpected complications before they happen for the well-being of millions of moms and babies. Complications such as preterm birth, preeclampsia and gestational diabetes, affect 1 in 5 pregnancies, with large economic costs and lifelong health consequences for mom and baby. Our ground-breaking RNA platform is first to predict unexpected complications months before symptoms appear by revealing the underlying biology of each pregnancy. This breakthrough opens a new window into pregnancy health, allowing women to act and their doctors to intervene before unexpected complications become a crisis. Detection of early disease, at the individual level, also promises more equitable care than the use of broad sociodemographic factors that often result in bias. The idea for Mirvie was sparked by the personal experience of one of the founders whose daughter was born prematurely. Our team of world-class scientists and entrepreneurs has brought to market category-first, noninvasive tests used by millions. As a women’s health organization, Mirvie’s team shares a common purpose: to create a world where every pregnancy is as healthy as possible for both mom and baby. The company is headquartered in South San Francisco, California.Position Summary:As a Data Scientist at Mirvie, you will help with analyses and modeling of the world’s largest biological pregnancy datasets across thousands of women and ten thousands of genes to find biological signals and patterns. This work includes guiding our assays, bioinformatic pipelines, and product strategies with learned insights. Your work will encompass the full suite of data science, from data cleaning through feature discovery/engineering and modeling.

The ideal candidate is adept at using large data sets to find molecular markers for model development, optimization and applying such models for future clinical molecular diagnostic tests in a regulated environment.

You must have strong experience using a variety of data mining/data analysis/statistical methods, building and implementing models, using/creating algorithms and creating/running model simulations. The successful candidate is creative and innovative, able to tackle challenging problems at hand.

The prospective candidate may have prior exposure in the fields of bioinformatics, genomics, or medical data analysis.

You will be communicating analysis results broadly within the company and to the research team.Responsibilities as follows, but not necessarily limited to:
  • Mine and analyze data from company databases to drive molecular marker discovery, modeling, statistical analysis towards developing new innovative products that serve prenatal women’s health
  • Work closely with other members of the data science team and world leading expert advisors to develop models for different pregnancy complications.
  • Clearly communicate results to different audiences, both through written reports and slides/presentationss
  • Full ML workflow: Data pre-processing, feature discovery, feature engineering, model development, model testing
  • Skills and Qualifications:
  • Master’s or PhD in data science, machine learning, statistics, mathematics, physics, computer science, computational biology or another quantitative field.
  • Experience building and applying advanced machine learning and statistics: e.g. GLMs, SVMs, tree-based models, CNNs, Bayesian modeling
  • Excellent knowledge of data science programming languages including R and/or Python and supporting machine learning/data science libraries, experience with workflow engines a plus.
  • Proficient working in a version control environment, e.g. GitHub/GitLab.
  • Experience in software development and testing, exposure to software deployment a plus
  • Experience with AWS cloud and Docker containers a plus
  • 3-5 years of experience working with big data, exposure to genomics data is a plus.
  • Passion for science and a keen interest in human biology and genetics.
  • Strong professional written and verbal communication skills.
  • A great team player