Job Description Summary

As a member of the probabilistic design team, you will contribute to the development of state-of-the-art probabilistic methods, engineering design tools, solving challenging real-world industry problems in the area of metamodeling/surrogates, machine learning, model calibration and validation, uncertainty quantification, optimization and robust design, inverse modeling, engineering analysis model validation for GE Aerospace and U.S. government projects.

Job Description

Roles and Responsibilities

The successful candidate for this position will participate in developing state-of-the-art probabilistic and machine learning methods and tools to deliver world-class solutions for new product introduction (NPI), services, energy transition, and the future of flight throughout the GE Aerospace company. You will also work with U.S. government partners to solve some of the most pressing global challenges. You will work in a multi-disciplinary team contributing to the applications for performing prognostics and optimizing structures and systems under uncertainty for performance, weight, and cost. Applications include turbo machinery, material and mechanical systems, additive manufacturing, sustainable aviation fuel, hybrid electric propulsion, and hydrogen-powered flight.

• Collaborate with GE Aerospace design and services communities in the development of methods for probabilistic design, machine learning and optimization
• Apply probabilistic design, machine learning and optimization methods to real-world industrial applications for NPI design and Services maintenance planning for GE Aerospace business
• Implement probabilistic design, machine learning and optimization methods into GE internal design and services tools.
• Train and coach GE engineers on probabilistic and machine learning methods and tools
• Lead and manage projects, people and funding

• Doctorate degree in Mechanical Engineering, Aerospace Engineering with at least 3 years industrial experience, or related discipline OR Master's degree in Mechanical Engineering, Aerospace Engineering, or related discipline with at least 8 years industrial experience
• Experience in probabilistic design, machine learning, and/or optimization of engineering components and systems
• Fundamental knowledge in probabilistic methods, machine learning, Bayesian methods, and optimization applied to engineering design problems
• Experience with leading government programs and proposal writing.
• Fundamental understanding of solid mechanics and tools used in structural analysis such as ANSYS or similar FE software
• Ability to develop, modify and utilize custom computer codes in various languages such as Python, C++, Matlab, Visual Basic, Perl, R, etc
• Legal authorization to work in the U.S. is required. We will not sponsor individuals for employment visas, now or in the future, for this job opening
• Must be willing to work onsite in Niskayuna, NY

• In-depth understanding and methods development experience in dynamic Bayesian networks, Bayesian networks, physics-base/physics-informed forecasting, time-series modeling, image-based surrogates, probabilistic deep learning, transfer learning, physics discovery, uncertainty quantification, model calibration, verification & validation, DOE/DACE, metamodeling, sensitivity analysis, and inverse design
• Experience in solving complex engineering problems using probabilistic and machine learning methods above
• Experience with mechanical design and analysis methods
• Experience with software development
• Experience with fracture mechanics
• Demonstrated interpersonal, leadership and communication skills in a global team environment
• Strong interpersonal skills and analytical skills
• Ability to work across all functions/levels as part of a team
• Ability to work under pressure and meet deadlines
• Excellent written and verbal communication skills