P

Pacific Northwest National Laboratory

National lab advancing energy, security, environment

Lead Data Scientist 4 - Geospatial Intelligence, Remote Sensing

Full-TimeDeadline 10/6/26
$166.8k - $275.2k/yr
Senior
Bachelor's, Master's, PhD
Seattle, WA, USA+1 moreMore locations: Richland, WA, USA
In PersonOn-site presence is required.
AI & Machine LearningApplied Machine Learning, Computer Vision
No H1B Sponsorship
US Citizenship Required

About the job

Requirements
  • A Bachelor of Science or Bachelor of Arts and at least 7 years of relevant work experience, or a Master of Science or Master of Arts and at least 5 years of relevant work experience, or a PhD with at least 3 years of relevant experience.
  • Expertise in GEOINT workflows, including experience with remote sensing platforms, multimodal data fusion, and advanced geospatial analytics.
  • Experience working with hyperspectral imaging data in the long-wave infrared, including developing and validating machine-learning-based detection, classification, and unmixing algorithms; full product pipeline experience including radiometric calibration, atmospheric correction, and geometric correction; strong spectral sensing fundamentals including radiative transfer, reflectance/emissivity, absorption features, signal-to-noise ratio/noise modeling, and sensor characterization; applying machine-learning techniques to hyperspectral data fusion for geospatial intelligence applications; and proficiency with hyperspectral analysis and visualization tools such as ENVI/IDL.
  • Experience working with Synthetic Aperture Radar (SAR) data, including complex/IQ and formed products; developing and validating traditional signal-processing and machine-learning-based detection and classification algorithms; end-to-end SAR image product conversion pipeline experience; proficiency with SAR rendering tools; and strong knowledge of SAR/RADAR theory fundamentals including wave propagation, scattering, speckle, Doppler/geometry, and calibration.
  • Hands-on experience and strong proficiency with geospatial analysis tools such as GDAL, GeoPandas, and Google Earth Engine, and machine-learning frameworks such as TensorFlow and PyTorch.
  • Experience training, fine-tuning, and applying deep-learning models for remote sensing and GEOINT applications, including Automatic Target Recognition (ATR), object detection, and segmentation, using models and frameworks such as YOLO, Detectron2, DINOv2, Segment Anything Model (SAM), Vision Transformers, and geospatial foundation models.
  • Experience deploying operational solutions and ensuring scalability and applicability in secure or mission-critical environments.
  • Proven success in proposal development and securing external funding to support technical work or research programs.
  • Experience working with or supporting national security mission sponsors such as the Department of Energy, Department of Defense, Department of Homeland Security, or similar organizations.
  • Strong communication and leadership skills, including the ability to present technical findings to diverse audiences and stakeholders and collaborate effectively within multidisciplinary teams.
  • Ability to obtain and maintain a federal security clearance.
  • U.S. Citizenship is required.
  • Applicants selected must meet eligibility requirements for access to classified matter in accordance with 10 CFR 710, Appendix B.
  • Selected applicants are subject to pre-employment and post-employment random drug testing and must demonstrate non-use of illegal drugs, including marijuana, for the 12 consecutive months preceding completion of the Questionnaire for National Security Positions.
  • Foreign national candidates who have not resided in the U.S. for three consecutive years are not eligible for the PIV credential and need a favorable Local Site Specific Only Federal risk determination to maintain employment; after meeting the residency requirement, they must obtain a PIV credential.
  • Employees must disclose any affiliation with the foreign government of a DOE-designated country of risk and recuse themselves from the affiliation or receive approval before their first day of employment.
Responsibilities
  • Design and implement innovative GEOINT data science solutions addressing technical challenges related to imagery analysis, object detection, data fusion, and geospatial workflows.
  • Serve as a principal investigator or co-principal investigator on projects or tasks that contribute to integrating multiple capabilities or interdisciplinary approaches.
  • Lead efforts to develop and deploy machine-learning pipelines that process and analyze large quantities of geospatial data in operational environments.
  • Mentor and guide junior staff to foster technical excellence and professional development within the team.
  • Explore and generate proposal and business opportunity ideas by identifying emerging national security needs related to GEOINT analytics.
  • Build and maintain external partnerships to increase the team's technical reputation and align project outcomes with sponsor priorities.
  • Collaborate with multidisciplinary teams, including software engineers, geospatial analysts, and operational mission specialists, to transition research outputs into usable, field-ready solutions.
  • Ensure compliance with quality, safety, and security standards in project tasks and model adherence to these standards.
Desired Qualifications
  • An advanced degree in data science, computer science, physics, mathematics, or a similar discipline.

About the company

P

Pacific Northwest National Laboratory

View

Pacific Northwest National Laboratory (PNNL) conducts scientific research in chemistry, Earth sciences, biology, and data science to advance energy resiliency and national security. Its work spans designing and running experiments, developing models and simulations, and analyzing large data sets to generate knowledge and practical tools that help improve energy systems, environmental stewardship, and security. PNNL differentiates itself through its interdisciplinary approach across multiple scientific domains and its role as a government-funded national lab focused on real-world challenges, enabling collaborations with industry, academia, and government partners. Its goal is to produce actionable scientific insights and deployable technologies that strengthen national resilience and energy infrastructure.

Company Size

1,001-5,000

Company Stage

N/A

Total Funding

N/A

Headquarters

Richland, Washington

Founded

1965

Get referred to Pacific Northwest National Laboratory

See people who can refer or advise you

Simplify Jobs

Simplify's Take

What believers are saying

  • PNNL won Genesis Mission work in 2026 across cleanup, weather, and energy.
  • September 2026 brought grid-monitoring commercialization, nuclear restart support, and Georgia Tech partnership expansion.
  • PNNL’s $35.0 billion contract ceiling and $4.1 billion backlog support long-duration hiring and research.

What critics are saying

  • Battelle cut 68 PNNL jobs in November 2025, signaling funding volatility.
  • The prime contract ends September 30, 2027, forcing renewal risk against DOE priorities.
  • PNNL depends on one customer, and any DOE budget shift hits the entire operation.

What makes Pacific Northwest National Laboratory unique

  • Deb Gracio leads PNNL’s 6,043-person, $1.66 billion DOE lab from Richland, Washington.
  • PNNL spans chemistry, Earth science, biology, and data science under one federal platform.
  • PNNL converts research into deployable tools, from Abaco memory systems to WRAPT wildfire mapping.

Help us improve and share your feedback! Did you find this helpful?

Benefits

Health Insurance

Dental Insurance

Vision Insurance

Health Savings Account/Flexible Spending Account

401(k) Company Match

Paid Vacation

Paid Holidays

Paid Sick Leave

Flexible Work Hours

Wellness Program

Mental Health Support

Tuition Reimbursement

Relocation Assistance

Childcare Support

Adoption Assistance

Fertility Treatment Support

Legal Services

Company News

American Nuclear Society
Oct 7th, 2026
GAIN announces fourth round of 2026 vouchers.

GAIN announces fourth round of 2026 vouchers. This week, the Department of Energy's Gateway for Accelerated Innovation in Nuclear (GAIN) announced three fourth-round fiscal year 2026 vouchers to support the development of innovative nuclear technologies. Each company will get access to specific capabilities and expertise in the DOE's national laboratory complex - in this round of awards, Oak Ridge, Argonne, and Pacific Northwest National Laboratories are named - and will be responsible for a minimum 20 percent cost share, which can be an in-kind contribution. The awardees: One company is developing a gasket for use with high-temperature molten salts, one is validating its microreactor design, and one is testing a process for water restoration at uranium mining sites. BNNT Materials, of Newport News, Va., will collaborate with ORNL to demonstrate that its boron nitride nanotube (BNNT)-based gaskets can "withstand molten fluoride and chloride salts while maintaining sealing performance, chemical stability, and durability under reactor-relevant conditions," according to its proposal. Utilizing ORNL's facilities and expertise, the company plans to test high-temperature exposure, leakage, permeability, thermal cycling, and material compatibility with the goal of developing a more durable gasket that could reduce leakage, maintenance, and costly downtime for high-temperature molten salt systems. Tam Fortis Solutions, of Marina Del Ray, Calif., will collaborate with Argonne to validate computational models of its microreactor design before finalizing the design for a zero-power criticality test. Argonne also will partner with the company to "evaluate operating and transient conditions, assess heat-pipe and moderator behavior, and identify uncertainties," the proposal said. Ur-Energy USA, of Casper, Wyo., will collaborate with PNNL to test selected apatite-based formulas to determine the ability to sequester heavy metals for water restoration following in situ recovery (ISR) uranium mining, with the goal of developing a treatment method that will reduce time, cost, and environmental impact of mining operations. In April, the company announced it had begun ISR operations at its Shirley Basin uranium mining site in central Wyoming.

Ocean News & Technology
Oct 5th, 2026
DOE selects 14 projects for Hydropower Testing Network vouchers.

DOE selects 14 projects for Hydropower Testing Network vouchers. * 5 October 2026 * Edited By: Lauren Ernst The US Department of Energy's (DOE's) Hydropower and Hydrokinetic Office (H2O) selected 14 hydropower projects to begin negotiations on vouchers for in-kind support through the Hydropower Testing Network (HyTN). Working with one of HyTN's 21 testing facilities, voucher recipients will improve the readiness of their hydropower technologies. "By pairing industry innovators with leading US test facilities and technical expertise, HyTN accelerates the development of next-generation technologies that keep hydropower reliable and abundant," said H2O Director Nichole Fitzgerald. Hydropower remains an important pillar of America's energy mix, accounting for nearly 6% of the country's total utility-scale electricity generation. Modernizing existing hydropower plants and implementing new technologies will help the United States meet its growing energy demand and drive down energy prices. By providing access to a wide range of testing capabilities, HyTN accelerates the development of hydropower innovations and helps ensure the United States can maintain and grow its hydropower systems in accordance with President Trump's Executive Order 14154, Unleashing American Energy. This is the second round of selections from HyTN, which offers access to more than 65 specialized physical testing and modeling capabilities ranging from hydraulic and biological testing to techno-economic analysis. The technology developers selected for this cohort have been matched with these capabilities, pending negotiations, based on their testing needs. The 14 selected projects are: * Dry Surface Technologies, LLC, based in Guthrie, Oklahoma, will work alongside Pacific Northwest National Laboratory (PNNL) to scale up the production of a non-toxic antifouling coating to a pilot-scale manufacturing process, providing a less expensive, non-toxic alternative for preventing clogged components, and reducing facility repairs. * Emrgy, Inc., based in Atlanta, Georgia, will demonstrate the prototype of a low-head turbine technology platform designed to generate energy from man-made water infrastructure like irrigation canals. * GenH, Inc., based in Somerville, Massachusetts, will test a rapidly deployable, low-impact technology to generate electricity from existing non-powered dams at the University of Minnesota. Results will inform a predictive framework that will help quickly design custom systems for different dams. * Hydro Green Energy, LLC, based in Birmingham, Alabama, will work with the National Laboratory of the Rockies to develop a grid-focused economic analysis for a pumped storage hydropower project at an existing dam and reservoir, facilitating advancement towards licensing and construction. * Kingsbury, Inc., based in Philadelphia, Pennsylvania, is investigating an advanced thermoplastic polymer as a possible bearing material for use in hydropower generators, continuing its work with Oak Ridge National Laboratory (ORNL) from the first round of HyTN. * Nucleic Sensing Systems, based in Saint Paul, Minnesota, will validate its real-time environmental DNA (eDNA) sensor, which monitors water for the presence of fresh, dissolved eDNA and distinguishes it from stale or transported eDNA. * Prometheus Innovations, LLC, based in Lafayette, Louisiana, will continue their work from the first round of HyTN, collaborating with PNNL to assess a coating that prevents harmful aquatic growth like invasive mussels and brown algae. * Prometheus Innovations, LLC will also work with PNNL to test an underwater net coating that can attract or repel fish to prevent them from swimming into water intake structures. * Public Utility District No. 1 of Chelan County, based in Wenatchee, Washington, will evaluate self-lubricating, grease-free wicket gate stem bushings at PNNL's tribological test facility, determining its effectiveness for upgrading hydropower infrastructure. * Public Utility District No. 1 of Chelan County will also work with PNNL to validate a low-temperature "cold spray" technique to repair worn hydropower turbine components on-site without using heat. * Radmantis, based in Toledo, Ohio, will use Verdantas' Fish Passage Survival and Behavior Steel Testing Flume Facility to continue their work from the first round of HyTN, evaluating whether mechanically guided fish entrainment improves AI-based selective fish passage at hydropower facilities. * RCAM Technologies, Inc. DBA Sperra, based in Boulder, Colorado, will work with Polaris EcoSystems to advance a 3D-printed subsea pumped storage hydropower system that stores electricity in hollow concrete spheres on the seafloor. * University of Washington's Applied Physics Laboratory, based in Seattle, Washington, will collaborate with PNNL to assess the reliability and durability of a small, low-cost sensor designed to monitor water quality for hydropower and pumped storage facilities in a more economically feasible way. * VBASE Oil Company, based in Pendleton, South Carolina, will continue their work from the first round of HyTN, collaborating with ORNL to test a lubricant for use in hydropower facilities. The HyTN voucher opportunity is funded by H2O and managed by ENERGYWERX in partnership with DOE, a collaboration made possible through a partnership intermediary agreement set up by DOE's Office of Technology Commercialization. Don't miss the headlines. ON&T's top news, every week. More in Energy

Macallan Communications
Sep 14th, 2026
PNNL, SEPA jointly provide new interactive map showing state-by-state wildfire legislation.

PNNL, SEPA jointly provide new interactive map showing state-by-state wildfire legislation. Toward enabling states to see how other states are tackling wildfire risks to the grid, the U.S. Department of Energy's Pacific Northwest National Laboratory (PNNL) and the Smart Electric Power Alliance (SEPA) have teamed up on a new interactive map that provides a nationwide view of state-by-state wildfire legislation. The Wildfire Regulation and Policy Tracker (WRAPT) shows what topics are prioritized over time, which states are pursuing which wildfire mitigation strategies, which measures passed or failed, and where an agency has stepped in to create a comparable statewide requirement. "Wildfire risks for utilities were once a Western issue but are now a national issue and moving fast," said Rebecca O'Neil, advisor for electricity infrastructure at PNNL. "States across the country can benefit from an interactive tool like WRAPT - from states in the West as they consider policy options and interactions, states in the Midwest as they consider best practices and get in front of this issue as it arrives, and states in the East adapting this playbook as they balance utility investment against the threat of wildfire." Research shows that in 2025, states considered more wildfire-related legislation than they had during the previous 10 years combined. While PNNL had already been tracking legislation data in a much simpler dataset over the last year, SEPA last spring launched its own review of state legislation for its Wildfire Technology Roadmap. After a chance encounter with the PNNL team at a conference and comparing notes, SEPA saw an opportunity to transform PNNL's dataset into an interactive map. WRAPT shows users a broader, more accessible view of state-by-state wildfire legislation. Currently, the map shows 44 legislative and regulatory actions across 18 states. PNNL and SEPA plan to update the map as new actions are introduced. "SEPA has spent years helping the industry make sense of the policy shifts reshaping the grid, and wildfire governance is now one of the fastest-moving fronts," said Jared Leader, SEPA's senior director of Resilience and Global Initiatives. "WRAPT reflects the kind of work SEPA is built for: pairing PNNL's research with our sector perspective to translate policy developments across states into something decision-makers can act on." WRAPT also offers an alternative for those involved in wildfire mitigation planning who would otherwise have to search through hundreds of documents cast in state-specific contexts buried within bill management systems in state legislative sessions, O'Neil said. With WRAPT, users can select a state and quickly see what approaches it has considered. The new map also helps states tackle practical questions: What have other states tried? Which bills became law? Which proposals failed? What issues are regulators addressing? What lessons can be applied directly state-to-state and what would need to be adapted? "The partnership with SEPA is helping move wildfire risk research beyond the laboratory and into the hands of people making decisions," said O'Neil. "The more that state officials and regulators can understand why different states are making different choices, the easier it is for them to interpret and make the right choice for themselves."

GCN
Sep 6th, 2026
PNNL, Fervo and NVIDIA build AI digital twin to run geothermal reservoirs in real time.

PNNL, Fervo and NVIDIA build AI digital twin to run geothermal reservoirs in real time. A federal laboratory, a geothermal developer and an AI computing company announced on June 22, 2026, that they are jointly building an AI-powered virtual replica of an enhanced geothermal reservoir, a tool its creators say could eliminate weeks-long analysis waits that today leave underground power plants operating below their potential. What EGS-Twin is and how it works. Fervo Energy, NVIDIA and Pacific Northwest National Laboratory (PNNL) announced an agreement to develop a next-generation digital twin platform for Enhanced Geothermal Systems (EGS) technology, known as EGS-Twin. EGS-Twin is designed to deliver real-time insight into subsurface behavior and operational performance through the integration of high-resolution field data with physics-based modeling and AI-driven forecasting. Fervo Energy deploys fiber-optic cables and uses acoustic technology to map and gather intelligence from the subsurface, but processing and analyzing all that data takes too much time for operators to act swiftly. Fluctuations in the operating data can indicate issues in wells, reservoirs or pipelines that may require attention. Current models that help represent the dynamics of a geothermal system can take weeks to run. EGS-Twin would run in real time and allow operators to respond quickly to any underground problems that may arise. To build EGS-Twin, PNNL researchers will use Fervo's industry expertise and field data to train scalable AI models on NVIDIA AI infrastructure. The trained AI models will then be integrated into the NVIDIA Omniverse libraries, helping geothermal operators more quickly identify and respond to subsurface changes, optimize power generation, and strengthen the scalability of enhanced geothermal systems. Data sources and the road to commercial deployment. Using currently available proprietary field data from Fervo's Nevada and Utah sites, the PNNL team will begin training the digital twin immediately and continue refining the platform as additional production data comes online, with the platform scheduled for implementation by 2029. The final EGS-Twin will contain anonymized data so that other geothermal plant operators can adapt it to their own operations. That open-access design matters in an emerging industry where a broader, standardized modeling tool could compress the learning curve for every developer that follows. Fervo's CTO and co-founder Jack Norbeck said: "We believe that digital twins will expedite the learning curve for geothermal development as we build and operate our GeoBlock assets." He added that "integrating high-fidelity physics-based models with AI-driven forecasting has the potential to reshape reservoir management, improve heat recovery, and enhance system reliability." Fervo's Cape Station context. Fervo established Project Red in Nevada in 2023, which now generates 3 megawatts for the grid. Cape Station Phase I will deliver 100 megawatts (MW) of baseload clean power to the grid beginning in 2026, and Cape Station Phase II will bring an additional 400 MW online by 2028. Fervo is building its Cape Station plant in Beaver County, Utah, which is expected to begin delivering electricity to the grid later this year and will ultimately generate 500 megawatts. Cape Station is expected to be the largest next-generation geothermal development in the world. Geothermal made up just 0.4% of all electricity generated in the United States in 2023. But according to the U.S. Department of Energy, geothermal could provide potentially 90 gigawatts of firm and flexible power to America's grid by 2050, assuming that enhanced systems like Fervo's catch on as a widespread renewable energy option. Getting there will depend partly on whether operators can extract more from each plant they drill, which is precisely the problem EGS-Twin targets. Why real-time reservoir intelligence matters now. The EGS-Twin partnership reflects a wider convergence of AI infrastructure and baseload power ambitions. As GCN has reported, only 13 percent of US power projects in the grid interconnection queue reach commercial operation, a failure rate that presses every geothermal developer to demonstrate that operating plants can perform reliably once they are running. Poor real-time visibility into reservoir conditions is one of the operational risks that can knock capacity factors well below the round-the-clock figures written into power contracts. Maruti Mudunuru, the PNNL Earth scientist leading the project as principal investigator, said that "current modeling capabilities for geothermal systems are too slow to fully incorporate and analyze production data, which can lead to an underutilized resource," and that a working digital twin would allow EGS operators to "understand, in real time, the dynamics of their reservoir and act quickly to maximize the power generation potential." The team will use currently available results to begin training the digital twin and will continue developing it as additional production data comes online. The platform is expected to be up and running by 2029. The development also connects directly to the broader push to make geothermal a viable baseload option for data-center power demand. Federal support for EGS has expanded on multiple fronts this year, from Pennsylvania shale conversions to multi-state consortia, and EGS-Twin represents one of the first efforts to apply large-scale AI infrastructure to the operational side of that buildout. Hugo Rojas is the editor of GCN. With a Master of Science in Engineering, he specializes in technology, data, and science, and brings a human-centered perspective informed by psychology.

Interesting Engineering
Sep 5th, 2026
Oceans contain billions of tonnes of uranium.

Oceans contain billions of tonnes of uranium. The attraction of seawater uranium is the sheer size of the potential resource. Known uranium resources on land are estimated at around 7.9 million tonnes, while the world's oceans are estimated to contain approximately 4.5 billion tonnes of uranium. Much of it entered the oceans over geological timescales as uranium was weathered from rocks and carried into the sea. For countries expanding nuclear power, that could represent a potentially enormous additional source of nuclear fuel. China is particularly dependent on uranium imports. According to the World Nuclear Association figures cited by South China Morning Post (SCMP), Chinese mines produced about 1,600 tonnes of uranium in 2024, compared with roughly 13,000 tonnes required by its nuclear reactors. The US has spent decades investigating whether seawater could help close this gap. Researchers at Oak Ridge National Laboratory and Pacific Northwest National Laboratory developed and tested uranium-absorbing fibers in natural seawater, including experiments at Washington's Sequim Bay. The US program ultimately found that the economics remained unfavorable compared with conventional land-based mining. PhosCage has so far only been demonstrated under controlled laboratory conditions. The Qingdao researchers collected seawater off the coast of Qingdao and processed 25 liters through a laboratory flow system rather than deploying the material directly in the ocean. Large-scale ocean deployment would introduce challenges involving currents, waves, fouling by marine organisms, material durability, recovery of the adsorbent, and processing costs. The researchers also did not provide a cost estimate for the uranium recovered in their experiments. They say their next steps include scaling up the material and reducing the overall cost of extracting uranium from seawater. Get the latest in engineering, tech, space & science - delivered daily to your inbox. You may unsubscribe at any time. Kaif Shaikh is a journalist and writer passionate about turning complex information into clear, impactful stories. His writing covers technology, sustainability, geopolitics, and occasionally fiction. A graduate in Journalism and Mass Communication, his work has appeared in the Times of India and beyond. After a near-fatal experience, Kaif began seeing both stories and silences differently. Outside work, he juggles far too many projects and passions, but always makes time to read, reflect, and hold onto the thread of wonder.