PI: Simon Billinge

This position is open both to materials scientists with computing experience and Data scientists with an interest in materials science and physics

The Data Science Institute (DSI) at Columbia University invites applications for the position of a Postdoctoral Research Scientist focused on the application of machine learning applied to neutron diffraction and spectroscopy techniques in the group of Professor Billinge, funded by US Department of Energy, Office of Science, Office of Basic Energy Sciences.

DSI strives to be a force for change. We advance the state-of-the-art in data science; transform all fields, professions, and sectors through the application of data science; and ensure the responsible use of data to benefit society.

Drawing on Columbia's strengths in computer science, statistics, and industrial engineering and operations research, DSI was launched in 2012 to unite our expertise and a University-wide interest in this revolutionary approach. The University is a trailblazer in the field and is uniquely poised to expand data science to every corner of the institution.

We train the next generation of data scientists, develop innovative technology, foster collaborations in advancing techniques to interpret data and address pressing societal problems, and work closely with industry to bring promising ideas to market.

PROGRAM DETAILS

The goals of the project are to use data analytic (AI, ML) methods to to leverage the very high dimensional input parameter space of a time of flight neutron experiment to separate signals from different components of a sample. There is growing need to understand the structure-property relationship of materials in real operating devices. Experiments to do this, operando measurements, involve running a real operating device in an x-ray or neutron beam and tracking changing signals as the device operates. A huge challenge in this regard is to separate signals from different components of the device that are in the beam, some of which are interesting and others not. This project aims to use AI/ML to do the signal separation in an automated way.

The project will involve developing novel data analytic (AI, ML) algorithms, and implementing them in software (primarily Python), to extract component signals from large datasets of complex overlapped signals.

KEY RESPONSIBILITIES

The successful candidate will work closely with scientists on the team and will be expected to be involved with data acquisition at experiments, but principally with data reduction and analysis, and be expected to work effectively in a team environment with the combined University and National Laboratory context. Experimental expertise is not a prerequisite, but experience with data analysis and AI/ML is preferred.

MINIMUM QUALIFICATIONS:

• Ph.D. or equivalent degree in computer science, applied mathematics, materials science, chemistry, physics, earth science, data science, engineering or related field

• Demonstrated ability in Python programming, a knowledge of machine learning methods and a demonstrated ability to write research papers in the academic literature and to make clear scientific presentations

• An ability to work well in a team environment

PREFERRED QUALIFICATIONS:

• Knowledge of x-ray, neutron or electron diffraction/scattering, x-ray absorption spectroscopy, synchrotron radiation experiments, data analysis, data science, software development in general and python programming in particular;

• Experience in, and knowledge of, xray/neutron/electron diffraction and/or pair distribution function (PDF) methods;

• Knowledge of databases, cloud computing, parallel computation, open-source code development experience and other software infrastructure related skills are also valuable skills.

We encourage applications from candidates with diverse backgrounds, experiences,and identities.

Columbia University is an Equal Opportunity Employer / Disability / Veteran

Pay Transparency Disclosure

The salary of the finalist selected for this role will be set based on a variety of factors, including but not limited to departmental budgets, qualifications, experience, education, licenses, specialty, and training. The above hiring range represents the University's good faith and reasonable estimate of the range of possible compensation at the time of posting.