Machine Learning Research Intern

RWE•Austin, TX

About The Position

The Machine Learning Research Intern will work at the intersection of atmospheric science, renewable energy, and advanced AI. This role focuses on developing diffusion models for mesoscale downscaling, ML-driven data-cleaning systems, and supervised learning approaches to quantify turbine performance losses from atmospheric conditions. You will work on real operational datasets and contribute research that transitions into production systems used across large wind portfolios.

Requirements

Working on a degree in Business, Information Science/Technology, and a strong interest in renewables
Strong Python skills (TensorFlow/Keras, NumPy, Pandas, xarray)
Exposure to diffusion or generative models
Excellent grasp of object-oriented programming
Strong GitHub workflow experience
Comfort working with messy, real-world datasets
Strong written and verbal communication
Team-oriented, curious, and self-drive

Nice To Haves

Atmospheric science, physics, or energy systems background
Experience with mesoscale or reanalysis models (WRF, ERA5)
Knowledge of uncertainty quantification or physics-informed ML
Experience moving research into operational pipelines

Responsibilities

Develop diffusion-based generative models for high-resolution wind field reconstruction and downscaling
Build supervised and unsupervised ML pipelines for cleaning meteorological time-series and metadata
Create supervised learning models to predict power-performance losses from atmospheric variables
Write clean, object-oriented Python code using TensorFlow/Keras and scientific libraries
Collaborate through GitHub with structured PRs, reviews, and version control
Work directly with domain experts and data owners to acquire and understand raw datasets
Use LLM tools productively for coding and debugging while remaining technically independent