Assistant Computational Scientist: AI for Spectroscopy and Elemental Imaging

Argonne National Laboratory•Lemont, IL

1d•$94,486 - $147,399

About The Position

The Advanced Photon Source (APS) (https://www.aps.anl.gov/) at Argonne National Laboratory invites applicants for an assistant computational scientist staff position to develop and apply artificial intelligence (AI) and machine learning (ML) methods for x-ray spectroscopy and spectromicroscopy. This role will focus on advancing the state-of-the-art in spectroscopy across fluorescence mapping and imaging, x-ray absorption near-edge structure (XANES), extended x-ray absorption fine structure (EXAFS), and related multimodal spectroscopy workflows. The successful candidate will: Lead a research program focused on creating novel computational methods and AI-driven approaches for challenging analysis and inverse problems in x-ray spectroscopy. Be responsible for developing and implementing advanced algorithms and AI/ML models for denoising, deconvolution, spectral fitting, unmixing, chemical-state identification, uncertainty-aware interpretation, and multimodal data fusion across fluorescence, XANES, EXAFS, and related experiments, with the goal of accelerating data analysis, improving quantitative accuracy, and enabling autonomous experiments. Explore the use, adaptation, and fine-tuning of modern foundation models for scientific data analysis, representation learning, and multimodal reasoning in x-ray science. Work closely with beamline scientists and participate in data-intensive experiments, reporting results in high-impact publications and at international conferences. May be required to perform other duties as assigned. This position is part of the Computational science and AI group (CAI) (https://cai.xray.aps.anl.gov/), a team of cross-disciplinary experts in ML, applied mathematics, high-performance computing, and x-ray science. The appointee will benefit from access to world-leading experimental and computational resources at Argonne, including the upgraded APS and the exascale Aurora supercomputer. Candidates are encouraged to include a cover letter in addition to a CV.

Requirements

Bachelors and 5+ years’ experience, Masters and 3+ years’ experience, PhD and 0+ years’ experience, or equivalent
A deep understanding of the physics of x-ray spectroscopy and spectromicroscopy, including fluorescence, XANES, EXAFS, or closely related techniques.
Demonstrated expertise in the associated algorithms and computational methods, such as spectral analysis, fitting, inverse problems, statistical inference, and related quantitative workflows.
Proven experience in developing and applying AI/ML models to scientific problems in the context of spectroscopy, imaging, scattering, or related physical sciences.
A strong publication record demonstrating innovation in computational methods or AI applied to x-ray spectroscopy, spectromicroscopy, or a closely related field.
Experience with deep learning (DL) libraries such as PyTorch, TensorFlow, or JAX, and familiarity with modern foundation models and transfer learning approaches.
Proficiency in programming, particularly in Python.
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

Hands-on experience with data acquisition and analysis from x-ray fluorescence, XANES, EXAFS, or related spectroscopy and spectromicroscopy experiments.
Experience with version control (e.g., Git) and collaborative software development practices.
Experience with high-performance computing (HPC) and/or cloud environments.
Familiarity with computational modeling or domain-analysis packages relevant to x-ray science, materials characterization, chemistry, or spectroscopy.

Responsibilities

Lead a research program focused on creating novel computational methods and AI-driven approaches for challenging analysis and inverse problems in x-ray spectroscopy.
Be responsible for developing and implementing advanced algorithms and AI/ML models for denoising, deconvolution, spectral fitting, unmixing, chemical-state identification, uncertainty-aware interpretation, and multimodal data fusion across fluorescence, XANES, EXAFS, and related experiments, with the goal of accelerating data analysis, improving quantitative accuracy, and enabling autonomous experiments.
Explore the use, adaptation, and fine-tuning of modern foundation models for scientific data analysis, representation learning, and multimodal reasoning in x-ray science.
Work closely with beamline scientists and participate in data-intensive experiments, reporting results in high-impact publications and at international conferences.
May be required to perform other duties as assigned.