Jobs
>
San Carlos

    PdM Algorithm Development Engineer Novity Inc - San Carlos, United States - PHM Society

    PHM Society
    PHM Society San Carlos, United States

    6 days ago

    Default job background
    Description


    Novity, a spin-out from Xerox's Palo Alto Research Center (PARC), brings truly predictive maintenance (PdM) technology to the industrial manufacturing sector to reduce costly unplanned downtime.

    The Novity solution is an Industrial Internet of Things (IIoT) technology that uses IIoT sensors and proprietary algorithms to enable industrial manufacturers to see the future health of their production assets.

    The Novity TruPrognosticsTM engine relies on a combination of machine learning and physics-based models of equipment.

    This allows Novity to predict equipment failures with 90 percent or better accuracy and lead times of months, not weeks or days.


    Novity has an immediate opening for a Predictive Maintenance Algorithm Development Engineer with a background in chemical process modeling, or modeling in related process industries, such as oil and gas, food and beverage, wastewater, or similar.

    The ideal candidate will be passionate about developing solutions for customers that provide a step change in value to their reliability and maintenance programs.

    Strong candidates will be able to leverage their deep domain expertise and advanced technical skills to develop state of the art diagnostics and prognostics algorithms for industrial IoT applications.

    The Algorithm Development Engineer will contribute to a modular library of algorithms and models that will be deployed as part of Novity's predictive maintenance software suite for a wide variety of customers in the process industries.

    The Algorithm Development Engineer needs to be comfortable with engaging in the end-to-end process of remote monitoring which includes all steps from data collection to analytics results presented back to customer.

    This position is a remote position with a strong preference for San Francisco Bay Area candidates.


    Responsibilities will include:
    Developing physics models of industrial equipment typically found in process industries.

    Developing algorithms for online fault detection, diagnostics, and prognostics.

    Validating models and algorithms with a variety of data sources, including simulated data, experimental data and customer data.

    Directing experimental lab tests, including defining test plans, determining data collection requirements, post-processing data and reporting results.

    Documenting technical information and communicating it to R&D team members, sales, marketing, management and external stakeholders.

    Support defining and delivering customer solutions, including instrumentation requirements, algorithm specifications, technical proposals, etc.


    Work in close collaboration with the software and hardware engineering teams, ensuring that algorithms are appropriately deployed in production environment.


    Collaboration with a diverse set of individuals including modeling scientists, data scientists, software and hardware engineers, sales engineers, plant operators, and process industry executives.

    Supporting market research in various process industries and adjacent market verticals.


    Required experience:
    M.S. or Ph.
    D. in an engineering field (mechanical or chemical engineering preferred, Ph.
    D. preferred).

    At least 3 years of experience in one or more of the following:

    Predictive maintenance or condition monitoring algorithm development for the process industries (oil and gas, chemical, wastewater, etc.).

    Chemical process modeling and optimization.

    Computational physics (CFD/FEA/Multiphysics) applied to industrial equipment, such as heat exchangers, separators, reactors, etc.

    Programming experience in Python, Matlab, or similar scientific computing language.

    Familiarity with production software development tools and concepts, including:CI/CD pipelines

    Functional and unit tests

    Source control systems

    Object-oriented design

    Integrated development environments

    Debugging tools

    Applied knowledge of data science methods including exploratory data analysis, statistics, feature extraction, data visualization, etc.


    Preferred experience and skills:
    Experience implementing production machine learning models.

    Familiarity with industry standards for process control equipment, maintenance, reliability, and monitoring, such as API, ASME, ANSI, ISA, etc.

    Familiarity with model-based reasoning, particularly model-based prognostics.

    Experience with process or design failure modes and effects analysis (FMEA).

    Experience reading process and instrumentation diagrams, process flow diagrams, and similar.

    Intellectual curiosity, as evidenced by a demonstrated ability and willingness to learn new technologies.

    Strong oral and written communication skills as evidenced by the research output of a graduate-level scholar.

    If interested, please contact Daniel Nelson at at

    #J-18808-Ljbffr