Applied Energy Research Data Scientist

Idaho National Laboratory•Idaho Falls, ID

About The Position

The AI Models & Digital Twins team develops AI to analyze real-world energy assets in near-real time, from the materials used in them to the grids they power. The Applied Energy Research Data Scientist turns complex real-world data into models that inform decisions, working with domain experts and engineers to build, validate, and deploy AI models and digital twins that reflect the behavior of physical energy systems. The role may be hired at Level 4 or Level 5, depending on the depth and breadth of the candidate’s proven experience and skills. It involves leading sponsored research, advancing data science and machine learning methods, developing funding opportunities, publishing and presenting research, advising collaborators, and mentoring staff. The position maintains a 9x80 schedule, with every other Friday off. Potential work locations include Idaho Falls, Idaho; satellite offices in Salt Lake City, Utah; and potential remote work options.

Requirements

  • Level 4: Master’s degree in data science, engineering, mathematics, computer science, physics, autonomy, super intelligence, or a related technical discipline and 6 years of relevant experience; or a PhD in the same fields and 4 years of relevant experience.
  • Level 5: Master’s degree in data science, engineering, mathematics, computer science, physics, autonomy, super intelligence, or a related technical discipline and 8 years of relevant experience; or a PhD in the same fields and 6 years of relevant experience.
  • Demonstrated record of lead-author, peer-reviewed journal publications in applied data science, machine learning, or computational modeling.
  • Demonstrated experience securing competitive research funding and serving as a principal investigator or technical lead on sponsored research.
  • Expert proficiency in scientific computing and machine learning tools, such as Python, PyTorch or TensorFlow, and scikit-learn, and experience deploying analytics across varied computational environments.
  • Ability to interpret and communicate data-driven results in an engineering or physical sciences context to technical and non-technical audiences, including sponsors.

Nice To Haves

  • Recognized expertise in energy generation, energy resources, or power systems, including reactor, thermal, geothermal, grid, or integrated energy system applications.
  • Experience with physics-informed machine learning, surrogate modeling, digital twins, or uncertainty quantification for complex natural or engineered systems.
  • Experience working with instrumented, operational, or spatially distributed data, such as sensor time series, plant monitoring, geospatial and remote sensing datasets, anomaly detection, or predictive maintenance.
  • Established relationships with DOE program offices, federal sponsors, or industry partners in the energy sector.
  • Experience mentoring staff and leading multidisciplinary or cross-organizational research teams.
  • Active leadership in professional societies and service on technical review panels or editorial boards.
  • PhD in an engineering, physical sciences, or earth sciences discipline, such as nuclear, mechanical, chemical, or electrical engineering; physics; geosciences; or applied mathematics.

Responsibilities

  • Serve as principal investigator or technical lead on research projects, defining scope, directing technical execution, and delivering results aligned with laboratory milestones and sponsor expectations.
  • Lead the development, validation, and interpretation of scientific and machine learning models and data pipelines for physical, natural, and engineered systems, using data from high-fidelity simulation codes, instrumentation, field and remote sensing, and operational records.
  • Apply and advance explainable AI and machine learning, large language models, physics-informed machine learning, uncertainty quantification, systems performance analysis, and data and sensor fusion methodologies.
  • Use energy systems and engineering, physical sciences, or earth sciences domain knowledge to identify and originate opportunities for machine learning and data-driven analysis in energy generation, resource characterization, operations, and research programs.
  • Evaluate model outputs using domain expertise to ensure physical consistency, accuracy, and operational relevance.
  • Develop proposals and secure funding for self and others from DOE program offices, other federal agencies, and industry sponsors; advise sponsors and customers on technical direction.
  • Publish high-impact research as lead author in peer-reviewed journals and present technical work to sponsors, customers, and external conferences.
  • Serve as a technical advisor to subject matter experts across INL and external collaborators, and lead technical and peer reviews as requested.
  • Mentor early-career staff, post-docs, and interns, and contribute to building the technical capability of the group.
  • Build and sustain a national professional network; lead initiatives within professional associations and contribute to technical review panels, journals, and agency reviews.
  • Collaborate with sponsors, customers, universities, and industry partners, demonstrate and champion INL values, and work independently with minimal supervision on complex, loosely defined research problems.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service