AI/Machine Learning Research Scientist (Remote Eligible)

Oak Ridge National Laboratory•Oak Ridge, TN

2d•$145,170 - $177,430•Remote

About The Position

We are seeking a Machine Learning Research Scientist who will support the development of fundamentals for GeoAI imagery processing, self-supervised learning methods for large vision-language models to enable downstream imagery perception tasks including object detection and counting, visual question answering, semantic segmentation, and change detection. This position resides in the GeoAI Research Group in the Geographic Data Science Section, Geospatial Science and Human Security Division, National Security Sciences Directorate, at Oak Ridge National Laboratory (ORNL). As part of our team, you will support research tasks related to image preprocessing pipelines including pansharpening, geocoding, atmospheric compensation, image denoising, cloud masking, finetuning large geospatial foundation models for a variety of national security downstream tasks. The GeoAI Group is part of the Geospatial Science and Engineering Division (GSED) at ORNL. The group conducts cutting edge research and publishes from novel machine learning based solutions to large scale geospatial application solutions. Research activities include the design of efficient image preprocessing pipelines, machine learning workflows using high performance computing techniques, and conducting post-processing and validations of model of outcomes. Under the guidance of senior research scientists, the selected applicant will take roles on multidisciplinary teams supporting cutting-edge research and engineering projects, deploying workflows on large-scale computing environments, leveraging ORNL’s Frontier for its dense GPU-based high-performance computing resources to train large GeoAI models.

Requirements

A PhD degree in electrical engineering, civil engineering, geoinformation science, or a related discipline
A minimum of 4 years of applied experience
Hands-on experience with training machine learning models on high performance computing infrastructures leveraging GPU accelerators
Experiences building satellite imagery preprocessing workflows
Experience using Python or other programming languages to develop AI algorithms in PyTorch computing framework

Nice To Haves

Experience working with spatio-temporal datasets and remote sensing imagery
Knowledge of distributed computing and uncertainty quantification
Ability to function well in a fast-paced research environment, set priorities to accomplish multiple tasks within deadlines, and adapt to ever changing needs

Responsibilities

Develop and execute accelerated imagery preprocessing pipelines for high resolution satellite imagery
Develop and execute workflows to support finetuning large geospatial vision models
Collect, process, and analyze large volumes of satellite imagery
Support the design and implementation of efficient computer vision techniques
Visualize and communicate research results through technical reports, and peer-reviewed publications
Collaborate with other research and technical professionals on new methods to advance GeoAI methods
Deliver strong science and engineering artifacts demonstrating research innovation for our sponsors
Enable ORNL’s mission by aligning behaviors, priorities, and interactions with our core values of Impact, Integrity, Teamwork, Safety, and Service. Promote diversity, equity, inclusion, and accessibility by fostering a respectful workplace – in how we treat one another, work together, and measure success