Genomic Data Scientist

Job ID:
Job date: 2017-08-04
End Date:

Company : Second Genome 

Country :

Role : Research Scientist 


[Click Here to Access the Original Job Post]

Job Description:
You are a computer scientist, data scientist, or computational biologist with a passion for deriving actionable insights from large datasets. You understand that your findings may impact workflows companywide, and you stand by your results. You are personally driven but are comfortable not having all the answers; you know how to find the resources you need to achieve your goals. You accept the changing demands of an industry environment. Multitasking comes naturally to you. You are a team player and you understand the importance of communication and the balance between compromise and assertion.

Responsibilities and Duties:

  • Develop, train, validate, and deploy best-of-class statistical models for predicting protein function from large metagenomic datasets
  • Engineer novel and informative features from biological sequence data to improve predictive models
  • Develop in-house platform and pipelines for managing and querying metagenomic data using software development lifecycle principles
  • Actively seek, evaluate, and spearhead the adoption of new computational approaches to expand internal capabilities
  • Communicate findings within the group and to stakeholders inside and outside the company
Qualifications and Skills:
  • Formal education and experience with machine learning methods and advanced multivariate statistics, particularly with small-n-large-p datasets
  • Knowledge of feature selection methodologies and model validation strategies to minimize false discovery rates
  • Fluency in Python and its numerical, scientific, and parallel computing libraries
  • Familiarity with MySQL or similar query language, R and Unix shell command line tools
  • Ability to effectively explain complex computational approaches to individuals from different disciplinary background
  • Committed to integrity, accountability, transparency, and reproducibility; results that can’t be reproduced by another are meaningless
  • Ph.D. in Computer Science, Applied Mathematics, Bioinformatics, or comparable (Master’s degrees considered)
Additional Qualifications:
  • Familiarity with prokaryotic biology, biological sequence data, and contemporary tools for analyzing and operating on biological sequences
  • Knowledge of public bioinformatics databases and their APIs
  • Background or training in numerical methods for optimization, especially combinatorial optimization and genetic algorithms
  • Proficiency in visualization and presentation of large scale -omics data
  • Familiarity with cloud computing using Amazon AWS or comparable service
  • Strong interpersonal communication skills
  • Two or more years of industry experience


Requeriments :

Skills :

Areas :


Additional Info:
About Us:

We are a fast-paced and innovative venture backed biotechnology company seeking tomorrow’s breakthrough therapeutics at the interface of complex microbial communities and their host environments. We are leaders in microbial ecology, metagenomics, and computer science. Our informatics team actually interacts with our lab scientists to propose and develop novel scientific hypotheses for testing. We love fresh approaches, we value process validation, and we welcome peer review.

Second Genome perks:

  • Competitive salary and employee stock options.
  • Catered lunches and fully stocked snacks and beverages.
  • Four weeks paid time off and holidays.
  • A fantastic, comprehensive medical, dental, and vision plan options.
  • 401(k) plan, pre-tax commuter benefits, and flex spending accounts.
  • Monthly “wellness” subsidy.
  • Apple computer, and other technology.
  • Friendly office environment with great colleagues, and a culture that drives innovation, passion, collaboration and fun!

[Click Here to Access the Original Job Post]