Postdoctoral Appointee: Surrogate Modeling of Stochastic Dynamical Systems in Epidemiology - Hybrid
- Sandia National Laboratories
- Location: Livermore, CA
- Job Number: 7188443 (Ref #: 691921)
- Posting Date: Oct 25, 2023
Sandia National Laboratories is the nation’s premier science and engineering lab for national security and technology innovation, with teams of specialists focused on cutting-edge work in a broad array of areas. Some of the main reasons we love our jobs: + Challenging work with amazing impact that contributes to security, peace, and freedom worldwide + Extraordinary co-workers + Some of the best tools, equipment, and research facilities in the world + Career advancement and enrichment opportunities + Flexible work arrangements for many positions include 9/80 (work 80 hours every two weeks, with every other Friday off) and 4/10 (work 4 ten-hour days each week) compressed workweeks, part-time work, and telecommuting (a mix of onsite work and working from home) + Generous vacations, strong medical and other benefits, competitive 401k, learning opportunities, relocation assistance and amenities aimed at creating a solid work/life balance* World-changing technologies. Life-changing careers. Learn more about Sandia at: http://www.sandia.gov*These benefits vary by job classification. What Your Job Will Be Like: Sandia National Laboratories' Computational Data Science department seeks a postdoctoral researcher excited to develop and apply novel machine learning methods to agent-based epidemiological models. These models support enhanced and accelerated pandemic response and both Sandia’s fundamental research and national security missions. The research will develop explainable, data-driven surrogate models that capture complex, multi-scale disease progression dynamics by combining scientific computing and machine learning (Scientific Machine Learning). The position requires deep knowledge of machine learning (ML) and its use in the modeling of nonlinear dynamical systems, dimensionality reduction, and some knowledge of statistical inference and spatial modeling. The candidate must be able to conduct original research (as evidenced by publications) and be adept at programming (as evidenced by code development expertise). The work will be performed with an interdisciplinary research team spread over academia, Lawrence Livermore National Laboratory and Sandia. The research team’s strengths lie in computational mathematics, computational science, high performance computing, scientific software development, uncertainty quantification, and machine learning algorithms. On any given day, you may be called on to: + Research, develop, implement, and validate novel scientific machine learning models capable of predicting epidemic dynamics + Collaborate on both fundamental methods and software development to support high-quality, reproducible research + Work efficiently and independently under the supervision of two senior Sandia technical staff members + Interact with a multi-institution team of theorists, computational scientists, and domain experts + Publish outstanding new developments in peer-reviewed scientific journals and internal technical reports; present work to team members and the larger scientific community This job is based in Livermore, CA, or Albuquerque, NM, however virtual workers located in any U.S. State or District of Columbia may be considered. Regular or periodic travel to your assigned work location and other sites may be required. Applicants on this requisition may be interviewed by multiple organizations at Sandia National Laboratories. Qualifications We Require: + PhD conferred within five years of employment in computational science, computer science, applied mathematics, statistics, data science, or a related engineering or science field + Research experience in one or more of the following areas: differential equations, optimization, scientific machine learning, complex systems, epidemiological models, probability theory, uncertainty quantification, or other relevant areas + Experience with machine-learning approaches in scientific computing, e.g., surrogate models, reduced order models, inverse problems, and data-driven or hybrid methods. + Familiarity with at least one high-level scientific programming language (e.g., Julia, Python, Matlab) + To be eligible for this position, applicants must be legally authorized to work in the United States of America without sponsorship for employment visa status Qualifications We Desire: + Familiarity with compartmental models (i.e., ordinary differential equations), neural networks as universal approximators, and spatial diffusion modeling + Experience with Neural Ordinary Differential Equations (NODE) and/or Universal Differential Equations (UDE) + Background in solving practical problems in science and engineering that involve real world data + Ability to work in Linux, MacOS, and High-Performance Computing (HPC) environments + Strong written and oral communication skills + Ability to work on a team to solving complex interdisciplinary R&D problems relevant to DOE missions + A dedication to fostering an inclusive R&D environment, as demonstrated by your application materials + Research community leadership through activities such as participation in student or professional organizations, service on committees, workshop and/or conference organization, and editorial roles About Our Team: The Computational Data Science Department (8738) conducts fundamental research, develops, and applies algorithms at the nexus of machine learning and computational science and engineering models. Team members develop foundational theory, algorithms, and tools, and partner to enable data-guided decision support for science and engineering mission applications. The department emphasizes fundamental, open research in new methods, notably Bayesian inference, machine learning, reduced-order modeling, and V&V/UQ. As part of the Center for Computation & Analysis for National Security (8700), we’re dedicated to anticipating and reducing national security risks through cross-domain computational and analytical capabilities with an inclusive and hybrid workforce. Posting Duration: This posting will be open for application submissions for a minimum of seven (7) calendar days, including the ‘posting date’. Sandia reserves the right to extend the posting date at any time.
This position does not currently require a Department of Energy (DOE) security clearance. Sandia will conduct a pre-employment drug test and background review that includes checks of personal references, credit, law enforcement records, and employment/education verifications. Furthermore, employees in New Mexico need to pass a U.S. Air Force background screen for access to Kirtland Air Force Base. Substance abuse or illegal drug use, falsification of information, criminal activity, serious misconduct or other indicators of untrustworthiness can cause access to be denied or terminated, resulting in the inability to perform the duties assigned and subsequent termination of employment. If hired without a clearance and it subsequently becomes necessary to obtain and maintain one for the position, or you bid on positions that require a clearance, a pre-processing background review may be conducted prior to a required federal background investigation. Applicants for a DOE security clearance need to be U.S. citizens. If you hold more than one citizenship (i.e., of the U.S. and another country), your ability to obtain a security clearance may be impacted. Members of the workforce (MOWs) hired at Sandia who require uncleared access for greater than 179 days during their employment, are required to go through the Uncleared Personal Identity Verification (UPIV) process. Access includes physical and/or cyber (logical) access, as well as remote access to any NNSA information technology (IT) systems. UPIV requirements are not applicable to individuals who require a DOE personnel security clearance for the performance of their SNL employment or to foreign nationals. The UPIV process will include the completion of a USAccess Enrollment, SF-85 (Questionnaire for Non-Sensitive Positions) and OF-306 (Declaration of for Federal Employment). An unfavorable UPIV determination will result in immediate retrieval of the SNL issued badge, removal of cyber (logical) access and/or removal from SNL subcontract. All MOWs may appeal the unfavorable UPIV determination to DOE/NNSA immediately. If the appeal is unsuccessful, the MOW may try to go through the UPIV process one year after the decision date. EEO: All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, age, disability, or veteran status and any other protected class under state or federal law. NNSA Requirements for MedPEDs: If you have a Medical Portable Electronic Device (MedPED), such as a pacemaker, defibrillator, drug-releasing pump, hearing aids, or diagnostic equipment and other equipment for measuring, monitoring, and recording body functions such as heartbeat and brain waves, if employed by Sandia National Laboratories you may be required to comply with NNSA security requirements for MedPEDs. If you have a MedPED and you are selected for an on-site interview at Sandia National Laboratories, there may be additional steps necessary to ensure compliance with NNSA security requirements prior to the interview date. Job ID: 691921
All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, or veteran status.