Bioinformatics Scientist, Machine Learning

Guardant Health   •  

Redwood City, CA

Not Specified years

Posted 278 days ago

This job is no longer available.

Company Description


We believe conquering cancer is a big data problem. That’s why we built the world’s leading comprehensive liquid biopsy. This non-invasive tool for accessing and sequencing tumor DNA is used by thousands of oncologists to help tens of thousands of advanced cancer patients. We believe the boom in cancer data acquisition we helped launch will drive important discoveries and new products. We’re working on some exciting ones, including in early detection, where the impact on patients can be profound. We’ve raised more than $500 million from investors including Sequoia Capital, Khosla Ventures, OrbiMed, and SoftBank.

Job Description

At Guardant Health, we are committed to positively and significantly impacting patient health through technology breakthroughs that address long-standing unmet needs in oncology.

 As the leader in the field of liquid biopsy, Guardant Health has collected cancer genomic data from over 40,000 patients and is looking for machine learning data scientists excited about developing statistical and machine learning algorithms aimed at using this data to enable breakthroughs in cancer patient care.

 Potential applications of machine learning using liquid biopsy data include (but are not limited to):

  • Using epigenetic signals to detect tissue of origin
  • Identifying biomarkers predicting drug response
  • Predicting the occurrence of cancer relapse
  • Detecting tumor residues after surgery
  • Enabling early detection of cancer in high risk patients


  • Use machine learning and signal processing techniques to develop new algorithms for NGS data analysis with impact on clinical patient care
  • Elucidate key dependencies and factors explaining observed mutational profiles across cancer types
  • Integrate internal and external genomic data sources for comprehensive analysis
  • Interact with medial affairs and technology teams to include expert knowledge of data attributes and to design experiments generating most pertinent data for analysis
  • Participate in brainstorming sessions, create and maintain a highly productive and motivating work environment
  • Provide written documentation and specifications


  • PhD. in machine learning, high dimensional statistics, computational biology, engineering, mathematics, physics or related fields
  • Experienced machine learning algorithm developer with focus on genomic data applications:
  • Experience using regression, supervised and unsupervised learning
  • Experience using deep learning applications to genomic data
  • Expert knowledge of probability and statistics with focus on working with high-dimensional data
  • Experienced in Python, R, and C/C++
  • Familiar with high-performance computing (SGE / grid, Mesos, MPI)
  • Great communicator with great written and verbal fluency in English
  • Ability to work independently, with minimal supervision
  • Dedicated to make a difference in a rapid-paced startup environment