AFERA Framework in Action: AI- Digital Twin Data Center Thermal Management
Listed on 2026-07-22
-
Research/Development
Data Scientist, AI Business & Operations
Organization
National Energy Technology Laboratory (NETL)
Reference Code
NETL-Postdoc-2026-Guenther
How to Apply
A complete application consists of:
- An application with academic history, work history, honors, and awards
- Description of your goals, related experience, and related skills – refer to NETL’s Core Competencies and ongoing projects when applicable
- Transcripts (see transcript information)
- A current resume/CV with academic history, employment history, relevant experiences, and publication list
- Two educational or professional recommendations (contact information for at least two recommenders)
All documents must be in English or include an official English translation.
For questions before, during, or after you submit an application, please contact NETLinfo.
Final date to receive applications
7/31/2026 3:00:00 PM Eastern Time Zone
Description
The National Energy Technology Laboratory’s (NETL) record of success has been built on understanding the future of energy and the technologies required to make that future possible. We have a legacy of developing technologies that addressed acid rain in the 1970s and mercury in the early 2000s.
Program Goals
- Develop skills and knowledge in your field of study
- Engage with new areas of basic and applied research
- Network with world‑class scientists
- Exchange ideas and skills with the Laboratory community
- Use state‑of‑the‑art equipment
- Contribute to answers for today’s pressing scientific questions
- Collaborate with broader scientific and technical communities
Project Details
Through the Oak Ridge Institute for Science and Education (ORISE), this posting seeks a post‑doctoral researcher to engage in projects with the Research Innovation Center (RIC) at the National Energy Technology Laboratory (NETL) in the area of LDRD under the mentorship of Chris Guenther. The project will be hosted at the NETL Morgantown, WV campus.
The U.S. Department of Energy (DOE) is driving a transformative initiative to integrate Artificial Intelligence (AI) into scientific discovery, leveraging its capacity to accelerate complex physics‑based modeling and analyze vast datasets at unprecedented speeds. The proposal introduces the Applied Federated Energy Research Accelerator (AFERA), a framework for end‑to‑end applied energy research integrating Agentic AI, Applied Energy Solvers, Digital Twins, and Control & Automation.
The initial use case involves developing a comprehensive digital twin for NETL’s Joule 3.0 Modular Data Center (MDC).
The Overall Objectives Of This Project Are Threefold
- Demonstrate the feasibility and advantages of the AFERA digital engineering approach to accelerate research.
- Develop a comprehensive AI‑based digital twin for NETL’s Joule 3.0 MDC as a use case for the AFERA approach.
- Provide detailed information on future investments needed at NETL to develop the infrastructure and research orchestration hub for leveraging the AFERA approach in future strategic DOE areas.
Stipend
Post‑Doctoral stipend: $7,860 per month.
Program Requirements
Participants are required to submit a pre‑appointment and post‑appointment survey, as well as a reflection on their appointment experience when they renew or end their appointment. The reflection should summarize their project(s), additional activities, and overall experience. Participants may also contribute to manuscripts, journal articles, book chapters, conference presentations, posters, patents, and other publications as part of their appointment.
Qualifications
Experience in using various artificial intelligence and machine learning tools and high‑performance computing methods to explore and develop digital twins is preferred. The following skills and knowledge are especially valuable:
- Programming: Python, MATLAB, C++, C
- Python / ML Libraries: Num Py, Pandas, PyTorch, scikit‑learn, Matplotlib
- ML Methods / Architectures: CNNs, LSTMs, GANs, kNN, graph neural networks
- Machine Learning: Predictive modeling, anomaly detection, supervised learning, deep learning, feature engineering, hyperparameter tuning, model evaluation
- Data & Modeling: Data preprocessing, dataset curation, time‑series analysis, simulation‑based validation, statistical analysis,…
(If this job is in fact in your jurisdiction, then you may be using a Proxy or VPN to access this site, and to progress further, you should change your connectivity to another mobile device or PC).