Bioinformatics Research Scientist

The Position:

We are seeking a talented and motivated Bioinformatics Scientist to join the within Veracyte’s Data Analysis Team (DAT). The individual will be responsible for analyzing transcriptomic and genomic data and applying machine learning models to Veracyte’s large database of cancer patient samples to identify clinically relevant signatures that improve our molecular understanding of disease pathology and progression. A core objective of this work is to build supervised and unsupervised models to predict different biological and clinical endpoints as well as define molecularly distinct subtypes. This position offers a unique opportunity to work with experienced professionals including academic and clinical researchers, practicing oncologists, and commercial partners with whom the candidate will discuss and present their work. These projects represent a critical part of Veracyte’s successful suite of research products, requiring a candidate that is passionate about computational biology, eager to learn, and who possesses strong analytical, problem-solving, and story-telling skills. 

KEY RESPONSIBILITIES: 

• Analyze both internal and external (including public) gene expression data with matched biological endpoints to build genomic signatures able to predict said endpoints.
• Assess and optimize existing gene expression models and improve their specificity and sensitivity.
• Develop and run NGS pipelines to call genomic alterations and analyze them in the context of clinical questions.
• Review and synthesize literature on cancer gene signatures and genomic alterations predictive of disease progression and treatment outcome.
• Explore and implement cutting edge machine learning models to further enhance our product offerings.
• Conduct statistical analysis and survival modelling for clinical events. 
• Produce professional visualizations, summarize analyses, and present results to both internal and external stakeholders.

Who You Are:  

• Ph.D. in Cancer Biology, Bioinformatics, Statistics or related field with 2 years of relevant post-graduate experience (postdoc or industry), or M.Sc. with 3-4 years of relevant industry experience (background in cancer genomics a plus).
• In-depth understanding of NGS pipelines and DNA-/RNA-seq analysis.
• Expertise in R programming and data analysis.
• Strong proficiency in feature reduction techniques and visualization (e.g., U-MAP), supervised and unsupervised learning algorithms, and model performance evaluation.
  • Hands-on experience with cloud-based compute architectures (AWS preferred).
• Excellent ability to summarize and communicate complex data findings with clarity.
• Ability to work effectively in a fast-paced and collaborative environment.

LOCATION: 

• This is a remote friendly position in US or Canada.
• On-site office available in South San Francisco or San Diego.

#LI-Remote