Postdoctoral Research Associate - Data Science for Advanced Manufacturing

Postdoctoral Research Associate - Data Science for Advanced Manufacturing

We are accepting applications for Postdoctoral Research Associate positions in Data Science for Advanced Manufacturing that will focus on the development of next-generation, data-driven manufacturing systems that integrate artificial intelligence, real-time sensing, and digital twins to transform how critical components are designed, produced, and qualified. The selected candidates will conduct research in data science and AI to develop scalable, deployable methodologies to assess and to improve manufacturing quality, efficiency, and certification readiness.

This position resides in the Manufacturing Systems Analytics group in the Digital and Secure Manufacturing Section, Manufacturing Science Division, Energy Science and Technology Directorate (ESTD) at Oak Ridge National Laboratory (ORNL). You will work at the MDF to advance digital manufacturing technologies and to accelerate their deployment to industry and national scale applications.

The MDF hosts a diverse set of advanced manufacturing systems - including powder bed, directed energy deposition, machining, polymer, and convergent manufacturing systems – used to produce critical components from advanced materials. These systems are instrumented and connected through a unified digital thread platform that captures multimodal, high-frequency data across the full manufacturing lifecycle, from process execution to post-process characterization. This environment enables the creation of high-fidelity digital twins and AI-ready datasets that support real-time monitoring, predictive modeling, and process optimization.

In this role, you will leverage large-scale, heterogeneous datasets to develop and deploy AI-driven methods for:

• Real-time quality monitoring and control of manufacturing processes
• Understanding relationships between manufacturing intent, machine behavior, and part performance
• Optimization of manufacturing processes for improved throughput, reliability, and quality

You will contribute to the development of integrated data and AI workflows that span data acquisition, modeling, and decision-making, including deployment at the edge and across distributed systems. You will have access to extensive experimental and computational resources and will be expected to publish research, present results, and contribute to high-impact programs. With over 100 manufacturing systems at the MDF, this role offers the opportunity to work on diverse, high-impact problems and to shape the future of intelligent manufacturing.

Major duties/responsibilities include:

• Develop and integrate imaging and other sensing modalities for data collection and monitoring in manufacturing environment
• Develop modular, extensible workflows for data processing
• Develop and deploy data analytics, machine learning, and statistical modeling methods for multimodal manufacturing datasets, including sensor streams, in-process signals, post-process characterization data, simulation outputs, and digital twin data.
• Develop, integrate, and evaluate AI/ML models for anomaly detection, predictive modeling, process optimization, and automated decision support, including real-time and edge deployment
• Collaborate with multidisciplinary teams to provide sensing, computational, and analytical expertise across projects
• Support broader research and development activities within the MDF

Deliver ORNL's mission by aligning behaviors, priorities, and interactions with our core values of Impact, Integrity, Teamwork, Safety, and Service. Promote equal opportunity by fostering a respectful workplace – in how we treat one another, work together, and measure success.

Basic qualifications:

• PhD. in mechanical engineering, material science, electrical engineering, computer engineering, computer science, data science, applied mathematics, or a closely related field
• Demonstrated experience with multimodal data acquisition, data analytics, statistical modeling, and machine learning in manufacturing environment.
• Proficiency in Python and common data science and machine learning libraries (e.g., Num Py, Pandas, Sci Py, scikit-learn, PyTorch, Tensor…