The Bay Area Environmental Research (BAER) Institute, a 501(c)(3) nonprofit organization

focused on enabling and conducting research in Earth and space science, is seeking a Data

Scientist for the NASA Ames Earth Science Division with experience in the areas of satellite

remote sensing and advanced data analytics including

This position will work with the NASA Earth Exchange (NEX; https://nasa.gov/nex) at NASA

Ames Research Center. NEX combines state-of-the-art supercomputing, Earth system modeling,

and NASA remote sensing data feeds to deliver a work environment for exploring and analyzing

terabyte- to petabyte-scale datasets covering large regions.

This position is located at NASAs Ames Research Center (ARC), Moffett Field, CA, and is

initially for 4 years with the possibility of extension. Telework and remote work may be

available and must comport with the position requirements.

Roles and Responsibilities:

Propose, plan, and achieve project or research objectives; technically guide and

participate in research projects and ensure all objectives are met

Design, train, implement, test, validate and apply machine learning algorithms and/or

statistical-based models using large, diverse datasets from multiple sources and complex

methods

Work with science team members to create visualizations, publications, and reporting

materials

Function as a subject matter expert on machine learning and statistical modeling for the

NEX group

Communicate solutions, methods, and techniques to both technical and non-technical

audiences

Write and execute complex workflows using scripting languages (e.g., Python, R) along

with the use of Relational Databases (SQL), NoSQL, Spark/PySpark, or some other

equivalent

Technical Qualifications:

Masters degree in computer science, machine learning, applied mathematics, statistics,

biostatistics, or relevant multidisciplinary degree

Proficiency in Python, R, and/or Julia

Knowledge of toolkits such as scipy, scikit-learn, PyTorch, TensorFlow, matplotlib, etc.

Experience manipulating large structured and unstructured datasets

In-depth understanding of linear models, multivariate analysis, stochastic processes,

sampling methods, Bayesian statistics, logistic regression, etc.

Have a detailed understanding of machine learning methods (, e.g., deep learning,

random forest, boosting, etc.)

Strong data visualization and data presentation skills

Excellent communication skills

Strong analytical and problem-solving skills with the ability to learn new information

quickly

Experience working with technical customers or science team collaborators

Preferred Skills:

Ph.D. degree in computer science, machine learning, applied mathematics, statistics,

biostatistics, or relevant multidisciplinary degree

Familiarity with more advanced machine learning methods such as reinforcement

learning, transfer learning, LSTMs, GANs

Familiarity with optical image processing, SAR image processing, multi-sensor

processing for the purposes of data analytics

Familiarity with high performance computing (HPC) environments

Familiarity with recent Artificial Intelligence (AI) industry developments

Familiarity with collaborative computational notebooks (e.g., Jupyter notebooks)

Hands-on work experience with Amazon Web Services (AWS) or other cloud service

providers

Familiarity working with Zarr, netCDF and HDF4/5 file formats

Familiarity working with both object store (S3) and POSIXs file systems with large

datasets

Experience with git, Jira are a plus