Full-Time
Assistant Physicist
Argonne National Laboratory
5,001-10,000 employees
Advanced scientific research and computing facilities
Compensation Overview
$94.5k - $147.4k/yr
Company Does Not Provide H1B Sponsorship
Woodridge, IL, USA
In Person
On-site position based in Lemont, Illinois.
PhD
 Academic & Institutional Research (1) |
|---|
Get referred to Argonne National Laboratory
See people who can refer or advise you
- Ph.D. in computer science, electrical engineering, computational physics, computational materials science, applied mathematics, or a closely related field.
- Demonstrated expertise in AI/ML applied to imaging or scientific data, including hands-on experience developing and deploying deep-learning models (e.g., CNNs, vision transformers, diffusion models, or related architectures).
- Strong scientific software development skills in Python and modern deep-learning frameworks (e.g., PyTorch, TensorFlow), including experience with distributed training on high-performance computing resources.
- Experience with high-performance computing (HPC) and/or cloud environments.
- Experience with version control (e.g., Git) and collaborative software development practices.
- Experience working with experimental imaging data, ideally at a synchrotron, electron microscopy, medical imaging, or comparable facility.
- Ability to work effectively both independently and in a collaborative, team-based research environment.
- 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.
- Design, develop, and deploy AI/ML tools for x-ray imaging operations including reconstruction, super-resolution, spatiotemporal fusion, denoising, segmentation, and feature extraction — and integrate them into the beamline software stack.
- Build closed-loop experimental workflows in which AI agents use streaming data and real-time reconstruction and analysis to steer measurement decisions, and contribute to the development of a fully autonomous, AI-driven tomography beamline as a flagship project for the group.
- Collaborate with the APS Computation and AI (CAI) group and engage with other APS AI efforts and activities to align Imaging Group tools with facility-wide AI/ML infrastructure, data services, and computing resources, and to contribute to shared frameworks for autonomous experimentation.
- Develop automated pipelines for acquisition, quality control, and downstream analysis that translate beamline-scientist expertise and currently manual operational steps into robust, reusable software.
- Build and maintain pipelines for robust metadata capture and the systematic generation of curated, standardized datasets to support continual AI/ML model training and validation.
- Provide on-site support for user operations and data collection across the X-ray Imaging Group beamlines, working directly with beamline staff and users during experiments.
- Contribute to the longer-term extension of AI-enabled automation and autonomy across Imaging Group modalities, including micro- and nano-tomography and high-speed imaging.
- Prepare experiments and instruments for remote and AI-driven operation.
- Present research results through publications, conferences, and scientific meetings.
- May be required to perform other duties as assigned.
- Experience developing AI/ML methods specifically for x-ray imaging, tomography, or high-speed imaging applications.
- Experience designing or contributing to automated, remote, or closed-loop ("self-driving") experimental workflows, including real-time data reduction, on-the-fly reconstruction, and AI-based experimental steering.
- Experience collaborating with facility-level computing, data, or AI groups to deploy software into production scientific environments.
- Experience handling high-rate, large-volume imaging datasets and developing high-throughput reconstruction or analysis pipelines.
- Experience contributing to open-source scientific software projects.
- Familiarity with metadata standards, data management, and curation practices that support reproducible science and ML training datasets.
- Familiarity with beamline data acquisition systems, detectors, or controls software, sufficient to integrate AI tools into operational workflows.
Argonne National Laboratory advances scientific discovery and sustainability by providing access to large-scale research facilities and high-performance computing for government, academia, and industry partners. Researchers use the Advanced Photon Source for atomic-level materials studies and the Argonne Leadership Computing Facility for complex simulations and data analysis. The lab differentiates itself through its shared-use, multi-institution partnerships and a focus on eco-innovation, net-zero goals, and AI accelerator development. Its aim is to address real-world energy, materials, and data science challenges by combining cutting-edge infrastructure with collaborative research efforts.
Company Size
5,001-10,000
Company Stage
Grant
Total Funding
$19.7M
Headquarters
Lemont, Illinois
Founded
1946
Get referred to Argonne National Laboratory
See people who can refer or advise you
Simplify's Take
What believers are saying
- UChicago Argonne LLC won a renewed DOE contract in 2026 for five years.
- 2026 launch of ChemGraph, GridMind, and AI inference services deepens Argonne's relevance.
- Activated Materials Lab opened in 2026, expanding nuclear fuels research and user-facility demand.
What critics are saying
- DOE's FY2027 request cuts Argonne funding about $155.8 million, hitting programs and construction.
- 2025 buyouts showed staff pressure; more layoffs follow if Congress accepts budget cuts.
- A prolonged federal reset or shutdown threatens APS, Aurora utilization, and Argonne's operating model.
What makes Argonne National Laboratory unique
- Aurora and APS create a rare AI-plus-X-ray discovery stack for 2026 science.
- Chain Reaction Innovations embeds startups inside Argonne with facilities, mentors, and DOE funding.
- Q-NEXT and other DOE centers keep Argonne central to U.S. quantum research.
Help us improve and share your feedback! Did you find this helpful?
Benefits
Health Insurance
Dental Insurance
Vision Insurance
Life Insurance
Disability Insurance
Paid Vacation
Paid Sick Leave
Paid Holidays
Remote Work Options
Flexible Work Hours
401(k) Retirement Plan
401(k) Company Match
Professional Development Budget
Wellness Program
Growth & Insights and Company News
6 month growth
↓ -2%1 year growth
↓ -2%2 year growth
↓ -2%Researchers at the US Department of Energy's Argonne National Laboratory have developed ChemGraph, an open-source framework that uses artificial intelligence to automate computational chemistry workflows. The tool provides a natural language interface, allowing researchers to describe scientific problems in plain language, which the system then maps onto computational tasks and analyses. ChemGraph was developed using resources at the Argonne Leadership Computing Facility, including the Aurora exascale supercomputer. The framework uses AI agents to handle different workflow tasks, from planning to execution and data aggregation. It calls appropriate scientific tools to reduce the risk of AI hallucination, using AI to run physics-based simulations rather than relying solely on existing knowledge. The framework supports applications in combustion efficiency, critical materials, and next-generation batteries, and complements DOE's Genesis Mission to accelerate science through AI.
The US Department of Energy's Argonne National Laboratory has launched an AI inference service using spare supercomputing capacity to support researchers across DoE labs and the Genesis Mission. The service runs on two clusters: Sophia, with 192 Nvidia A100 GPUs, and Metis, featuring 32 SambaNova SN40L AI accelerators. The platform provides secure access to various large language models, including OpenAI's GPT-OSS, Google's Gemma, and Meta's Llama, through a chatbot-like portal. Researchers are using the service to analyse experimental data in real time, including predicting plasma disruptions in fusion energy research and processing data from particle accelerators and telescopes. Argonne plans to extend the service to its Nvidia GH200-based Tara and B200-based Minerva systems, enabling scientists to experiment with AI without building their own infrastructure.
Researchers at the US Department of Energy's Argonne National Laboratory have developed GridMind, an agentic AI system designed to assist power grid operators through natural language interaction. The system functions as a reasoning co-pilot for control rooms, simplifying complex grid management tasks. GridMind employs a multi-agent architecture where specialised AI agents handle different functions, such as power scheduling and weather-based contingency planning. Large language models coordinate these agents to analyse situations, reason across different tasks and provide explainable recommendations. The system transforms technical analysis into conversational support whilst maintaining rigorous accuracy. Tests on standard power grid models demonstrated that GridMind consistently produced correct results across multiple state-of-the-art language models. The technology aims to accelerate decision-making by integrating disconnected workflows into a coherent reasoning engine.
A research team led by the US Department of Energy's Argonne National Laboratory has developed an AI adviser that optimises machine learning algorithms during autonomous experiments, accelerating discovery of advanced electronic materials. The system was applied to Polybot, Argonne's AI-guided robotic laboratory, to investigate mixed ion-electron conducting polymers for wearable electronics and energy storage. The adviser evaluates algorithm performance in real time and communicates insights to scientists who refine experimental plans. It reduced the study to just 64 experiments from over 4,300 possible combinations. During testing, the adviser suggested switching AI algorithms, leading to significant performance improvements, and identified deposition speed as a key performance driver. The research was published in Nature Chemical Engineering and included collaborators from the University of Chicago, Lawrence Berkeley National Laboratory and other institutions.
An energy and science incubator for transformative technologies