美國阿貢國家實驗室2023年招聘博士后職位（AI/ML用于高能X射線衍射顯微鏡）
美國阿貢國家實驗室（Argonne National Laboratory，簡稱ANL）是美國政府最早建立的國家實驗室，也是美國最大的科學(xué)與工程研究實驗室之一——在美國中西部為最大。阿貢前身是芝加哥大學(xué)的冶金實驗室 (Metallurgical Lab)，現(xiàn)在隸屬于美國能源部和芝加哥大學(xué)。諾貝爾物理學(xué)獎得主費(fèi)米于1942年在此領(lǐng)導(dǎo)小組建立了人類第一臺可控核反應(yīng)堆（芝加哥一號堆，Chicago Pile-1)，完成了曼哈頓計劃的重要一環(huán)，并且使人類從此邁入原子能時代。
Postdoctoral Appointee - AI/ML for High-Energy X-Ray Diffraction Microscopy
Argonne National Laboratory
Job Description
The X-ray Science (XSD) division at Argonne National Laboratory invites applications for postdoctoral researchers position for a project to develop artificial intelligence (AI) and machine learning (ML) methods to enhance high-energy X-ray diffraction microscopy at the Advanced Photon Source. The extreme volume and velocity of information associated with this non-destructive microstructure mapping technique can benefit from AI/ML at each stage of data flow, from the sensor to the data center. Because such tools can run at high speeds, thanks to advances in AI streaming inference accelerators, it becomes feasible to extract salient information from in-flight data, in real time, and thus both enabling fast feedback and reducing downstream computational burden. The successful candidate will conduct cutting-edge research in data science and deep learning and apply it to scientific problems, particularly in the materials science and engineering fields. The candidate will play a key role in developing physics-aware AI/ML models, developing workflow building blocks and implement high-speed training on data center AI systems (e.g., Cerebras CS-1 ML accelerator and Argonne's Aurora exascale supercomputer), end-to-end model training workflows and explore AI accelerators for simulation applications.
Position Requirements
Basic Qualifications:
·Ph.D. in material sciences and engineering or related field obtained within the last three years.
·Experience with X-ray science techniques (e.g., tomography, diffraction, etc.).
·Software development practices and techniques for computational and data-intensive science problems.
·Comprehensive experience programming in one or more programming languages, such as C, C++, and Python.
·Ability to provide project leadership.
·Exceptional communication skills, ability to communicate effectively with internal and external collaborators and ability to work in team environment.
·Ability to model Argonne’s Core Values: Impact, Safety, Respect, Integrity, and Teamwork.
·Understand, value, and promote diversity.
Preferred Qualifications:
·Experience with machine learning methods and deep learning frameworks.
·Experience on applied machine learning (e.g., successful projects that used ML to resolve scientific problems).
·Experience and skills in interdisciplinary research involving computer and material scientists.
·Experience with high-performance computing and/or scientific workflow.
