Job Description: & Qualifications
The Core-AI-ML research group, within Research and Advanced Engineering, is spearheading the process of discovery and democratization of AI-ML across all engineering function groups within the Ford product landscape. In order to realize a Ford vision of leadership, the Core-AI-ML research team, is looking for highly qualified and motivated candidates who are ready to take on challenging cross-functional problems that require discovery through fundamental research in directions that have so far received limited attention from the AI-ML community at large.
As part of the Core AI-ML team, in this role, you will be responsible for advancing the state-of-the-art in the general concepts and underlying mathematical constructs of machine learning as they apply to thermal, fluid, and multi-physics and other physics constrained engineering problems. In this role, you will familiarize yourself with and progress the understanding around the fundamental aspects of deep networks and their topologies as they apply to different problem spaces and data sets. This role therefore requires a strong mathematical background as well as an intimate knowledge of Machine Learning and/or knowledge of CFD, Heat transfer, and multi-physics problems. You will be responsible for identifying high impact problem statements and defining new directions of research. You will also work with practicing engineers in transferring these results into practical applications that help create product differentiation for Ford.
Take the lead on companywide research and development in the fundamental understanding of Machine Learning techniques including the mathematics of ML and /or developing full understanding of ML-DL applications in multi-physics engineering problems across diverse engineering domains and satisfy one or more of the requirements listed below.
Develop ML models that solve systems of ordinary differential equations/partial differential equations (ODE/PDEs) efficiently relative to competitive iterative solvers without sacrificing accuracy.
Provide generalizable ML solutions that leverage both data driven methods and physics models for providing high fidelity predictions over the full performance domain.
Develop sound understanding of the behavior of network architectures when dealing with non-stationary time series data.
Explore the potential for and suitability of gradient and non-gradient based methods in network learning.
Investigate robust methods and/or develop better architecture for memory/history integration in networks such as has been done with LSTM, GRU, RNN etc.
Develop ML based methods and tools, around high fidelity reduced order models, for fast, design verification, simulations as opposed to slow techniques such as DNS or LES.
Develop ML based methods and tools for fast identification of multi-physics problems using most suitable optimizers (gradient based, non-gradient based). Leverage DL tools like Tensor flow for efficient solutions.
Present and publish in reputed conferences and high impact peer reviewed Journals.
Publish internally and engage in internal knowledge dissemination through teaching, seminars as well as through any learning and development programs.
Develop research portfolio, for internal research as well as for research with leading universities, to allow Ford to maintain a leadership position in the industry
Master's Degree in Engineering, Mathematics, Statistics, Physics, Computer Science or related Science Degree
Must have at least one of the following for consideration:
Including course and/or research work have 1+ year of experience with simulation software for multi-physics, CFD and heat transfer problems.
Including course and/or research work have 1+ year of experience providing theoretical knowledge of AI/ML for progressing research in the areas of fluid, thermal and combustion systems or other multi-physics problems.
Including course and/or research work have 1+ year of experience with memory/history integration in networks such as has been done with LSTM, GRU, RNN.
Including course and/or research work have 1+ year of experience with multi-label classification, localization and detection (R-CNN, SSD, YOLO), transfer learning from (VGG, Resnet, Inception), features visualization, data augmentation.
Including course and/or research work have 1+ year of demonstrated proficiency in, Python and a common DL framework (PyTorch, Keras, Tensor Flow etc) and/or Matlab/Simulink and associated DL and optimization packages
PhD in Engineering, Mathematics, Statistics, Physics, Computer Science or related Science Degree
Strong background in mathematics, numerical methods, optimization, statistics and probability theory as it pertains to the broad field of ML and optimization for multi-physics engineering problems, CFD, Heat transfer etc.
Experience with CAD software such as CATIA, SolidWorks is a plus.
Knowledge of and experience in statistical and data mining techniques: generalized linear model (GLM)/regression, random forest, boosting, trees, text mining, hierarchical clustering, deep learning, convolutional neural network (CNN), recurrent neural network (RNN), T-distributed Stochastic Neighbor Embedding (t-SNE), graph analysis, principal components analysis (PCA), Typicality and Eccentricity Analysis (TEDA) etc is desirable
Familiarity with the basics of computational intelligence, and evolutionary computing, is a plus
Excellent problem solving skills, innovative thinking, and ability to identify, propose and lead new research projects that have a clear near and far value proposition
Passionate about keeping abreast of technical challenges, emergent trends and disruptive changes in ML especially as it pertains to multi-physics engineering problems
Excellent written/oral communication skills
Proven ability to work well with others as part of a diverse global team
Join our team as we create tomorrow! We believe in putting people first, working together, and facing challenges head-on, because we're Built Ford Tough. We're one team striving to make people's lives better while creating value, delivering excellence and ultimately going for the win.
Visa sponsorship may be available for this position.
Ford Motor Company is an equal opportunity employer committed to a culturally diverse workforce. All qualified applicants will receive consideration for employment without regard to race, religion, color, age, sex, national origin, sexual orientation, gender identity, disability status or protected veteran status.
Ford Motor Company US