See more Research Science jobs →

← Back to all jobs

Research Scientist - Optimization and Tool Automation

Posted

Siemens
Headquarters: Charlotte, NC
https://jobs.siemens-info.com
See all Siemens jobs →



For nearly 170 years, pioneering technologies and the business models developed from them have been the foundation of Siemens‘ success. Our central research and development unit, Corporate Technology (CT) plays an important role in this. Together with our global network of experts, we are a strategic partner to Siemens’ operative units and provide important services along the entire value chain – from research and development to production and quality assurance, as well as optimized business processes. Our support provided to the businesses in their research and development activities is ideally balanced with our own future-oriented research.

We at Corporate Technology are more than employees: We are actively helping to make people’s lives a little better every day. Would you like to be a part of that? Then join us. We offer you a high level of practical relevance as well as an opportunity to individually contribute your knowledge and your visions around the world. Whether you’re helping to develop products for the operating units or working in interdisciplinary projects for the business areas: At Corporate Technology you’ll be working in the heart of Siemens’ technological research together with the best.

Job Description:

We are currently seeking a Research Scientist who can develop science based models employing analytical computational models, methods and tools for predicting component level performance, behavior and remaining life assessment related phenomena for implementation in Engineering and Production Optimization tool chain for our facility in Charlotte location.

What are my responsibilities?

We are looking for an experienced professional in developing optimal automation tool chain for engineering & production multi-disciplinary optimization applications. You can either have a proven track record of multi-disciplinary optimization, design & engineering performance tool chain, digital manufacturing or optimization related work in industry, or research. For the former, please include your past projects. For the latter, please include your published papers, ideally at CVPR, ICCV, ACL, ICML, ASM, TMS, Applied Physics Journal, Acta Materialia or NIPS (publications at AAAI, UAI, AISTATS, KDD, ICDM, SDM, SC, IPDPS will also be considered).

This expert will be leading our research activities focused at extending computational techniques, methods and tools in domain of advanced manufacturing tool chain for design, engineering and production analysis for entire product lifecycle workflows.

Responsibilities in detail:
  • Research, design, and implement algorithms that power knowledge inference and online recommendations, based on end-to-end simulation framework, multi-disciplinary performance analysis, novel high performance computing algorithms to consume design and engineering data in real-time.
  • Dive into huge, noisy, and complex real-world behavioral data to produce innovative analysis and new types of predictive models of engineering behaviors and manufacturing processes performance.
  • Explore the untapped potential of big data for engineering, manufacturing and service analysis tasks and devise revolutionary approaches (should this be all 1 bullet?)
  • Development of multi-disciplinary tool chain for engineering and performance optimization, geometry parametrization.
  • Combined use of classical and first-principles based co-simulations methodologies to study and develop prediction tools to establish the cause of the drift of the performance in field or test and/or production variations
  • Advance the state-of-the-art in the field, including generating patents and publications in top journals and conferences.
  • Apply deep learning techniques to large-scale, real-world problems with proven collaboration experience with university and industry.
  • Fast prototyping, feasibility studies, specification and implementation of data analysis product components
  • Working with customers to understand algorithm requirements and deliver high-quality solutions in timely manner. Project planning, cost approval and proposing innovative problem solving solutions to business unit technical management.

Required Education, experience and skills:
  • Masters in Machine Learning, Mechanical Engineering, Aerospace Engineering, Computational Materials Engineering, Applied Mathematics or related field is required. PhD preferred.
  • Experience in Machine learning, Algorithmic foundations of optimization, Data mining or Machine intelligence (Artificial Intelligence) for creation of design & optimization tool chain for component design for high stiffness & temperature, aerodynamic drag reduction, optimal engineering iteration and close loop design modification incorporating test data and/or manufacturing variations and/or service data from usage.
  • 5+ years of related experience in the field of power generation and engineering, particularly gas turbines, steam turbines and generators.
  • Hands-on coding skills and ability to quickly prototype in Python, C++ is a must. Further experience in Scripting languages such as Java or LINUX environment tool chain is a plus.
  • Technical proficiency in languages such as Ansys, NX, R, WEKA, Pandas, Octave, Matlab, Python, Java, JavaScript, and C++
  • Hands-on advanced proficiency in handling and analyzing large data sets such as next-generation sequencing data.
  • Deep knowledge in optimal computational environment required for data processing, mining and machine learning is required.
  • Experience in optimization (Integer/Linear/Quadratic/Nonlinear Programming/Multi-objective/Stochastic) is a must.
  • Contribution to research communities and/or efforts, including publishing papers at conferences such at CVPR, ICCV, ACL, ICML, ASM, TMS, Applied Physics Journal, Acta Materialia, NIPS, AAAI, UAI, AISTATS, KDD, ICDM, SDM, SC, IPDPS et cetra
  • Outstanding written and verbal communication skills in English are required.
  • Excellent analytical and interpersonal skills and can do attitude. Strong collaboration skills and ability to thrive in a fast-paced environment, paired with the ability to work independently and prioritize work.
  • Successful candidate must be able to work with controlled technology in accordance with US Export Control Law. US Export Control laws and applicable regulations govern the distribution of strategically important technology, services and information to foreign nationals and foreign countries. Siemens may require candidates under consideration for employment opportunities to submit information regarding citizenship status to allow the organization to comply with specific US Export Control laws and regulations. Additional information on the US Export Control laws & regulations can be found on http://www.bis.doc.gov/index.php/policy-guidance/deemed-exports/deemed-exports-faqs?view=category&id=33#subcat34

Preferred Experience and Skills
  • Previous experience or knowledge in the field of finite element analysis, computation fluid dynamics, probabilistic reasoning, dimensionality reduction, decision trees, and performance analysis is preferred.
  • Familiar with metallurgy and mechanical behavior of material and must have a deep understanding of the relation between material-microstructure and property.
  • Experience with 1-3 classes of Artificial intelligence, Deep Learning algorithms in field of computer assisted engineering (CAE) technique like FEA, CFD and related technologies.
  • Preferred experience in collaborating with research organizations, universities and laboratories
  • Experience in implementation of translation research in field of CAE & related technologies for power generation industry
  • Familiarization with all aspects of manufacturing of gas and steam turbine components