Aerospace Machine Learning Engineer - Surrogate Modeling

Responsibilities

Submit your CV and any additional required information after you have read this description by clicking on the application button.

The candidate will support development and refinement of machine learning models to predict performance of aerospace vehicles.

The engineer will train machine learning models from system data and observation. The machine learning model will feature rapid inference times and be employed as a surrogate to more expensive physics-based solutions of systems for the Department of Defense (DoD), and other customers.

As new capabilities are needed, the engineer will support development and refinement of the models. The engineer will join a team of multi-disciplinary engineers to provide analysis and M&S of various airborne systems and subsystems.

These models will be used to support design studies and real-time applications. The engineer will be responsible for :

• Developing surrogate modeling techniques for efficient approximations of aerospace vehicles
• Demonstrating, validating, and verifying surrogate model accuracy
• Support integration of government tools, commercial tools, and in-house surrogate modeling tools

About the Group : CFD Research's Aerospace Data Science Group is developing a portfolio of traditional modeling and simulation and machine learning tools for supporting aerospace R&D.

This includes development of predictive machine learning and reduced-order models for (1) rapid estimation of aerospace vehicle properties;

2) optimal data collection; (3) affordable uncertainty quantification; (4) real-time performance for hardware in the loop applications, and (5) multi-disciplinary design optimization.

Basic Qualifications

• Candidate must be a US Citizen and meet eligibility to obtain / maintain a Security Clearance
• Position requires a Master's in Aerospace Engineering, Mechanical Engineering, Computer Science (or similar)
• 2+ years of experience with machine learning, response surface methods, kriging, or similar regression techniques
• Experience with transient, time-series predictive modeling
• Proficiency with the Python programming language
• Proficiency with version controlling through Git

Desired Qualifications

• PhD in Aerospace Engineering, Computer Science, Mechanical Engineering, or similar discipline.
• Knowledge of the PyTorch machine learning library
• Knowledge of formal gradient-based and gradient-free optimization techniques
• Experience with multi-disciplinary analysis and optimization (MDAO)

Location : This role is based in the Huntsville, AL area, and is 100% onsite.

About CFD Research : Since its inception in 1987, CFD Research has been a technology leader in engineering simulations and innovative designs.

CFD Research has worked with government agencies, businesses, and academia to provide innovative solutions within the Aerospace & Defense, Biomedical & Life Sciences, and Energy & Materials industries.

CFD Research has earned multiple national awards for successful application and commercialization of innovative technology prototypes, multi-physics simulation software, multi-disciplinary analyses, and expert support services.

CFD Research's impressive three-year growth rate was high enough to recognize the company in the Inc. Magazine's 5000 for the second year in a row.

Benefits : CFD Research offers competitive salaries and excellent employee benefits, including an employer matching 401(k) and Employee Stock Ownership Plan (ESOP).

CFD Research offers a highly competitive insurance package, including medical, vision, and dental insurance. We offer company paid leave, compensation time, parental leave, long-term disability, accidental death and dismemberment, and life insurance.

Performance appraisals occur twice a year and annual pay increases are based upon corporate goals, personal development, performance, and outstanding achievements.

In addition, group and individual bonuses are awarded for exceptional performance.

CFD Research is an EO employer - Veterans / Disabled and other protected categories

J-18808-Ljbffr