Senior Data Scientist / Machine Learning Engineer

Seattle WA
Organization: Phase Genomics
Application due date: 
Tue December 31, 2019
Position Type: Job

Phase Genomics uses cutting edge analytical techniques to draw novel insights from very large, rich datasets. We help scientists make breakthroughs in infectious disease, agricultural breeding, human health, cancer, biomanufacturing, food safety, and more. If you have great data science and/or machine learning chops and want to work on a technology that can have an actual impact saving lives, we’d love to meet you.


Phase Genomics is seeking smart, driven, creative data scientists and machine learning engineers to help create revolutionary new genomic and metagenomic assembly and analysis tools. Our data team is responsible for developing new-to-science analytical methods for deriving meaningful, actionable insights from data about the structure of chromatin in biological samples ranging from plants to animals to microbial communities to humans. Using modern deep learning techniques, we leverage these insights into information about newly discovered microbial species, plant and animal breeding characteristics, cancer and other human genetic/genomic disorders, and more. We are seeking an organized, talented bioinformatician with a proven track record in genome assembly, metagenomic assembly, biological data science, or related areas. The chosen candidate will be responsible for performing bioinformatics analyses using our entire scientific toolset, particularly in the fields of chromosome-scale genome scaffolding and metagenomic deconvolution using Hi-C and similar chromatin conformation data. They will also be responsible for developing new bioinformatics tools in these areas and for participating in R&D discussions and experimental planning with members of our wetlab team and other computational team members.

Every scientist and engineer on our team is given the opportunity for technical, architectural, and product-level ownership of their areas, and is expected to deliver world-class results. We value expertise, and our team is composed of people who are capable of owning a problem space top to bottom, yet still collaborate to deliver great results across the team.


Conceiving, designing, implementing, and maintaining deep learning or other analytical models to extract actionable insights from one or more areas of biological research. Areas include

  • Cancer-causing or cancer-implicated mutations
  • Human genetic/genomic disease
  • Metagenomics and microbial community analysis
  • Agricultural breeding and trait development (plants and animals)
  • Human microbiome health
  • Supporting services offered built on top of analytical models in a DevOps model
  • Helping define company technical and business strategy, especially connecting analytical approaches to product development and product strategy

While we are open to a broad range of backgrounds, a successful candidate will likely have the following qualifications:

  • 3+ years experience in developing software in an industry or graduate studies setting
  • Experience in at least one of the following software development settings:
    • Machine learning, especially deep learning
    • Data science
    • Statistical computing
    • Bioinformatics
    • Distributed data analysis
    • Physics, chemistry, astronomy, or other technical space with a big data/data science component
  • Experience with genomics is a plus, but not necessary.
  • Masters, PhD, or equivalent experience in computer science, software engineering, bioinformatics, or other technical fields with a programming bent
Bachelors degree