Data Scientist II - Machine Learning GEOINT and Remote Sensing

At PNNL, our core capabilities are divided among major departments that we refer to as Directorates within the Lab, focused on a specific area of scientific research or other function, with its own leadership team and dedicated budget.

Our Science & Technology directorates include National Security, Earth and Biological Sciences, Physical and Computational Sciences, and Energy and Environment. In addition, we have an Environmental Molecular Sciences Laboratory, a Department of Energy, Office of Science user facility housed on the PNNL campus.

The National Security Directorate (NSD) drives science-based, mission-focused solutions to take on complex,real-world threats to our nation and the world.

The AI and Data Analytics Division, part of the National Security Directorate, combines profound domain expertise and creative integration of advanced hardware and software to deliver computational solutions that address complex data and analytic challenges. Working in multidisciplinary teams, we connect foundational research to engineering to operations, providing the tools to innovate quickly and field results faster. Our strengths are integrated across the data analytics lifecycle, from data acquisition and management to analysis and decision support.

PNNL is seeking a Data Scientist II with experience applying deep learning to develop methods for detecting and classifying targets in electro-optical (EO) imagery or identifying targets and materials in hyperspectral imagery (HSI). This research supports geospatial intelligence (GEOINT) and national missions.

In the AI and Data Analytics Division, you will independently carry out defined research tasks as part of a team developing methods and tools that support intelligence analysis and national missions. Current priorities include automatic target recognition (ATR), long-wave infrared (LWIR) HSI target detection and material classification, and detection and classification with limited labeled training examples, particularly in EO imagery. The role also offers opportunities to explore related problems in remote sensing and intelligence analysis.

Candidates with deep learning experience in EO, HSI, or related sensing applications are encouraged to apply. You will work alongside researchers and domain specialists on difficult national science and technology challenges. Collaboration with software and machine learning (ML) engineers will reflect each project's needs and stage of development. Opportunities to advance existing research and pursue new ideas may come through ongoing projects, internal research investments, or new proposals.

• Apply and adapt deep learning methods to detection and classification problems.
• Investigate research questions through algorithm development, mathematical analysis, experiments, or implementation.
• Design reproducible experiments and compare methods, examining detection performance, classification errors, false alarms, and limitations.
• Document methods and results and work with software and ML engineers to integrate tested research code and algorithms into usable tools.
• Plan and carry out research tasks, discuss progress and challenges with project leads, and contribute ideas to research plans and proposals.
• Share technical knowledge across the team and mentor junior colleagues or students as appropriate.
• Follow applicable quality, safety, and security requirements.

This position is based in either Richland, WA or Seattle, WA and requires an onsite presence.

• BS/BA and 2 years of data science experience
  -OR-
• MS/MA
  -OR-
• PhD
• Experience applying deep learning to EO detection and classification or HSI target detection and material classification.
• Experience developing deep learning methods using PyTorch or another deep learning framework.

• Experience with the EO or HSI imaging chain, including sensor response, image formation, calibration, and data processing. LWIR HSI experience is particularly valued.
• Experience in addressing limited labeled training data or new target categories through methods such as few-shot learning, transfer learning, or open-vocabulary models.
• Experience with multimodal or temporal fusion for geospatial analysis, or agentic workflows that coordinate models, geospatial tools, and data sources, including evaluation of workflow reliability and analytic results.
• Experience developing or evaluating models for edge or onboard platforms with size,…