Postdoctoral Appointee - AI for Synchrotron Imaging

Argonne National Laboratory•Lemont, IL

4h•Onsite

About The Position

We are seeking a Postdoctoral Appointee to join the Computational Science and Artificial Intelligence Group in the X-ray Science Division of the Advanced Photon Source (APS) at Argonne National Laboratory to advance learning-enabled imaging methods. This position offers a unique opportunity for candidates with backgrounds in electrical engineering, computer science, applied mathematics, or physics to apply their expertise to challenging problems in computational imaging, while collaborating with leading experts in physics, biology, and environmental science. The APS at Argonne National Laboratory is a world-leading synchrotron facility recently upgraded to deliver nanometer-to-micron resolution imaging with dramatically increased X-ray flux. This makes it possible to visualize the interplay of soil structure and microbial life at scales bridging nanometers to millimeters, creating a unique opportunity to investigate how microbial communities are organized and interact within their natural environments.

Requirements

Ph.D. completed in the past 5 years or soon-to-be completed in Electrical Engineering, Computer Science, Applied Mathematics, Physics, or a related field.
Strong expertise in machine learning, computational imaging, computer vision, or signal processing.
Proficiency in scientific programming and modern ML frameworks, with the ability to implement and debug research-grade algorithms.
Demonstrated ability to work on complex data analysis problems and deliver robust computational solutions.
Excellent communication skills and a strong interest in interdisciplinary collaboration.
Ability to model Argonne’s core values of impact, safety, respect, integrity, and teamwork.
Interpersonal skills, oral and written communication skills, and ability to interact with people at all levels both within and outside the laboratory.

Nice To Haves

Experience with synchrotron or tomographic imaging datasets.
Background in inverse problems or physics-informed machine learning.
Exposure to scientific imaging applications (for example, biological, environmental, or materials science).

Responsibilities

Develop learning-enabled algorithms for 3D reconstruction of noisy and heterogeneous synchrotron datasets.
Implement adaptive acquisition strategies that guide beamline measurements in real time to increase efficiency and improve image quality.
Advance multimodal analysis methods that align and fuse structural, chemical, and biological signals to construct coherent models of microbial organization across scales.
May be required to perform other duties as assigned.