Postdoctoral Appointee - Neural Networks and Algorithms for Analog Neural Hardware
- Sandia National Laboratories
- Location: Livermore, CA
- Job Number: 7088827 (Ref #: 679426)
- Posting Date: Nov 11, 2021
Job DescriptionThis 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. : Sandia demonstrates its commitment to public safety in the national interest by requiring that all new hires attest to their vaccination status before commencing employment. The requirement also applies to those who are telecommuting and working virtually. Any concerns about the ability to meet this requirement should be directed to HR Solutions at (505) 284-4700. : We are seeking a postdoctoral appointee to develop neural network and machine learning algorithms to run on embedded analog hardware being developed by Sandia. We are developing new analog computing accelerators and are looking for someone to help develop algorithms tailored to the new hardware. We are developing a variety of applications including algorithms that run on satellites, autonomous vehicles, and airborne systems. You may add to projects that include developing recurrent neural networks, accelerators that output uncertain decisions, analog Fourier transforms, neural terrain correlation, sensor fusion, object detection and tracking, and more. This may involve developing algorithms that are resilient to noise and that are tailored to specific hardware constraints such as binary neurons or nonlinear weights. In addition to the neural algorithms, projects may include studying optimal ways to encode incoming data (i.e. analog pixels vs temporal filters (change detection) vs digital encoding [spikes]) and developing full data processing pipelines (all the way from initial sensing operations to eventual decisions). Our department is focused on developing new analog computing accelerators and works at all levels of design from materials, semiconductor devices, circuits, architectures, systems, and applications. We have designed accelerators for neural network inference, neural network training, solving linear systems, database systems and more. This position is focused specifically on neural network algorithm development, but there will be opportunities to interact with and add to other areas of our projects. On any given day, you may be asked to: + Develop hardware constrained neural networks for a variety of applications + Design and model new computing architectures + Develop new simulation tools + Conduct innovative research, publish and present results in refereed journals and conferences + Develop and pursue new opportunities in areas that support Sandia Mission activities + Work in multidisciplinary teams
+ PhD in electrical engineering, computer science, or a related area. + A record of publication and innovation, as evidenced by peer-reviewed journal articles, conference proceedings, technical books or issued patents. + Ability to hold a DOE Q clearance
+ Ability to work in a collaborative research environment on problems in a variety of domains + Proficiency in solving problems, prioritizing work, and making decisions + Excellent written and oral communication skills + Expertise in training and analyzing the behavior of neural networks including convolutional neural networks, recurrent neural networks and other probabilistic neural network models such as Bayesian networks + Strong mathematical and statistical background. + Experience working with large datasets and data engineering. + Proficiency with programming languages such as python + Experience with existing neural network frameworks like Tensorflow, Keras, and PyTorch + Expertise in modeling new system architectures that may compute using emerging memories or novel devices
The Digital Foundations & Mathematics department develops and maintains multiple technical capabilities. We develop and apply tools for the formal verification of digital systems, for electrical modeling and simulation analyses, and we develop computing accelerators for extreme environments. We are always interested in candidates with cross-disciplinary skillsets who can contribute to one or more of our programs.The formal verification activities include formal methods analysis of hardware and software; modeling and simulation of digital or software systems; synthesis of hardware (digital logic) or software to meet formal specifications; binary analysis (developing a custom lifter capability); and development of specialized software utilizing advanced mathematics to meet customer needs. The electrical modeling and simulation work includes printed circuit board level analysis of new systems in extreme environments, development of new capabilities in Sandia's internal PSPICE solver Xyce, and support for the Sandia device modelling teams.Our work on computing accelerators includes both modeling and designing novel fault tolerant architectures and new analog neuromorphic in-memory computing accelerators.Our department consists mostly of PhDs with backgrounds in computer science, analysis of programming languages and domain specific languages, high-performance computing, physics, electrical engineering, electrical circuit modeling & simulation & analysis, and neuromorphic computing architectures. We collaborate and team closely with organizations across Sandia and a broad spectrum of external partners.
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.
Sandia is required by DOE to conduct a pre-employment drug test and background review that includes checks of personal references, credit, law enforcement records, and employment/education verifications. Applicants for employment need to be able to obtain and maintain a DOE Q-level security clearance, which requires U.S. citizenship. 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. Applicants offered employment with Sandia are subject to a federal background investigation to meet the requirements for access to classified information or matter if the duties of the position require a DOE security clearance. Substance abuse or illegal drug use, falsification of information, criminal activity, serious misconduct or other indicators of untrustworthiness can cause a clearance to be denied or terminated by DOE, resulting in the inability to perform the duties assigned and subsequent termination of employment.
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. : This postdoctoral position is a temporary position for up to one year, which may be renewed at Sandia's discretion up to five additional years. The PhD must have been conferred within five years prior to employment. Individuals in postdoctoral positions may bid on regular Sandia positions as internal candidates, and in some cases may be converted to regular career positions during their term if warranted by ongoing operational needs, continuing availability of funds, and satisfactory job performance.
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.