Data Science and Engineering Fellow

Posted 13mins ago

Employment Information

Education
Salary
Experience
Job Type

Report this job

Job expired or something wrong with this job?

Job Description

Data Science & Engineering Fellow improving World Ocean Database pipelines for Intertidal Agency, an ocean-data nonprofit. Developing deduplication algorithms and open standards for global ocean conservation data.

Responsibilities:

  • Establish and help manage a project advisory committee of ocean data professionals
  • Work directly with major glider data providers, including IOOS, EGO, and IMOS, on upstream improvements to data submissions
  • Develop, test, and document an algorithmic method for identifying duplicate observations from gliders and other autonomous platforms and selecting which record to retain
  • Benchmark the method against the publicly served California Underwater Glider Network Line 80 record and NOAA NCEI’s glider holdings
  • Convene and run working sessions, including hackathons, with research software engineers, data scientists, WOD experts, and data-source specialists
  • Support workshop participants in implementing and iterating on workshop products within their own workflows
  • Release code, computational notebooks, and documentation publicly under open licenses
  • Prepare a peer-reviewed journal manuscript with the fellow as lead author
  • Work with project directors and the advisory committee to draft recommendations for the Intergovernmental Oceanographic Commission to support new standards and workflows

Requirements:

  • Quantitative and algorithmic capability, including multivariate statistics, dimensionality reduction, similarity and distance metrics, clustering or classification
  • Experience with record linkage, entity resolution, fuzzy matching, or deduplication
  • Working knowledge of blocking, indexing, approximate nearest neighbor search, or locality-sensitive hashing
  • Python fluency, preferably with numpy, pandas, and scipy
  • Version control with git
  • Comfortable in a Unix or Linux shell on a remote machine, with pipes, regular expressions, and standard text processing tools
  • Reading and writing netCDF, including CF conventions, standard names, fill values, and time units
  • Familiarity with CF discrete sampling geometries, particularly Profile and TrajectoryProfile, is a strong plus
  • Retrieving data programmatically from ERDDAP, THREDDS, or OPeNDAP endpoints and federal repositories, university archives, and cloud object storage
  • Ability to work independently on ambiguous problems without close supervision
  • Experience handling data from providers in formats not chosen by the candidate
  • Experience with government data infrastructure and modernizing legacy data systems
  • International research or data collaboration
  • Familiarity with oceanographic or earth science data
  • Ability to write readable, runnable code and collaborate across technical fluency levels

Benefits:

  • Fully remote workforce
  • 32 hour work week
  • Core working hours generally 0900-1300 Pacific Time, with some availability during UTC/Europe time
  • Estimated three weeks of travel for two project workshops plus the annual Climate Reserve convening
  • Excellent medical and dental benefits
  • Retirement savings
  • Generous vacation and sick leave policy
  • One-year Climate Reserve fellowship