Postdoc in ML for Plasma Physics & Multiscale Modeling

Los Alamos National Laboratory; Los Alamos (NM); On-site; USD 87,000 - 107,000; Full time

Benefits offered by this job

Medical insurance (PPO or HDHP)

Dental and vision insurance

Paid parental leave

Matching 401(k) and retirement plans

Relocation assistance

Job summary

Los Alamos National Laboratory (LANL) invites applications for a postdoctoral position in the T-5 Applied Mathematics and Plasma Physics group. The successful candidate will develop machine learning–enabled complexity reduction methods for multiscale plasma physics simulations, including reduced-order and surrogate modeling, uncertainty quantification, and scalable algorithms.

The role involves close collaboration with statisticians, applied mathematicians, and physicists within LANL and with

Qualifications

• Ph.D. in computational plasma physics, applied mathematics, computational science or closely related field, completed within the past five years or soon to be completed.
• Experience with Machine Learning for science applications
• Experience programming in Fortran, C++, Python
• Experience with numerical methods
• Demonstrated research ability with publications, reports, presentations, awards, etc.
• Excellent communication skills (oral and written)

Responsibilities

• Develop machine learning–enabled complexity reduction methods for multiscale plasma physics simulations.
• Explore reduced-order modeling, surrogate modeling, uncertainty quantification, and scalable algorithms for plasma applications.
• Collaborate with statisticians, applied mathematicians, physicists, and groups across LANL.
• Contribute to interdisciplinary research spanning national and international teams.

Skills

Machine learning for science

Excellent communication

Fortran

C++

Python

Numerical methods

Tools

Fortran

C++

Python

Job description

Los Alamos National Laboratory (LANL) invites applications for a postdoctoral position in the T-5 Applied Mathematics and Plasma Physics group. The successful candidate will develop machine learning–enabled complexity reduction methods for multiscale plasma physics simulations, including reduced-order and surrogate modeling, uncertainty quantification, and scalable algorithms.

The role involves close collaboration with statisticians, applied mathematicians, and physicists within LANL and with