Spire Global is seeking a data scientist to contribute to the Company’s effort of developing its portfolio of machine learning and statistical models for supporting our weather applications. This is an exciting opportunity for motivated scientists to improve the weather forecast through state-of-the-art predictive modeling, machine learning, statistical models and numerical optimization techniques using the available surface observations, numerical weather predictions models outputs, large amount of Radio Occultation (GNSS-RO), Reflectometry (GNSS-R) and other satellite data.
The position is located in Boulder, CO and the successful candidate will join the Statistics and Machine Learning group under the Global Validation Model branch.
The selected candidate will have opportunities to work with top-level scientists at Spire as well as scientists from around the world on issues that matter.
The successful candidate will work closely with software engineers, modeling and data assimilation teams’ members to implement and evaluate machine learning and statistical weather models and make use of large datasets of surface and satellite observations.
Responsibilities will include the following tasks:
Propose and implement innovative predictive modeling, machine learning and Bayesian inference approaches to increase the forecast skills of weather fields distributions.
Develop and implement state of the art weather post-processing techniques.
Explore different standard and non-standard data sources including Spire GNSS-RO and GNSS-R measurements, feature selection and sensitivity techniques to identify predictors for weather data-based models.
Working with meteorological data sets from various sources.
Working with the software engineering team to define most effective software solutions including transition to operations.
Presenting research findings at scientific conferences or workshops.
Applicants must have either a MS or PhD degree in Data Science, Computer Science, Applied Mathematics, or Atmospheric Science or equivalent working experience in machine learning algorithms and advanced statistical inference methods.
Working experience with linear/non-linear regression and classification methods and deep learning techniques including Generalized Linearized and Additive Models, Decision Trees, Clustering, Support Vector Machine, Neural Network, Multi-level models, Random Forests, Gaussian Processing, etc.
Working experience with combining multiple models and ensembles for predictive modeling and uncertainty quantification (Mixture models for density estimations, Bayesian Modeling Averaging, Ensemble Model Output Statistics, etc.)
Working experience with statistical inference methods for uncertainty quantification such as Bayesian inference and Adaptive Metropolis algorithms.
Working experience with numerical optimization and automatic differentiation techniques.
Working knowledge of Python, Fortran, Matlab, Linux scripting and code management practices.
Prior experience working with meteorological or oceanographic datasets (GRIB and NetCDF formats) in distributed computing environments.
Experience with modern software engineering principles and best practices including DevOps environment.
Demonstration of enthusiasm and ability to work in a development team that never stops improving predicting modeling techniques, statistical and machine learning methods and their outcomes.