Research Engineer I - High Speed Systems

ARCTOS TECHNOLOGY SOLUTIONS•Dayton, OH

6d•Onsite

About The Position

ARCTOS Technology Solutions, LLC (ARCTOS) is a fast-growing, technology-oriented small business providing aerospace, defense, and digital solutions, with offices and work sites across the United States. We’re looking for team-oriented innovators eager to tackle interesting challenges, work on important problems, and receive great benefits and employee support. ARCTOS is seeking a highly skilled and motivated Research Engineer to join our team supporting AFRL’s High Speed Vehicles Division. This role is focused on supporting the development of reusable hypersonic vehicle technologies specifically through advancing data-driven surrogate modeling capabilities to efficiently predict distributed and integrated aerodynamic loads as a function of vehicle deformation. The position involves developing reduced-order models, integrating multi-fidelity computational and experimental datasets, and applying hybrid physics/machine learning approaches to capture nonlinear and unsteady aerodynamic behavior. The successful candidate will combine expertise in aerothermoelastic modeling, machine learning, and reduced-order modeling to enable rapid, high-fidelity analysis for aeroelastic and aerothermodynamic applications.

Requirements

Experience with reduced-order modeling techniques
Experience with finite element analysis, high-performance computing
Knowledge of CAD, AFSIM, FEA programs, Python
Understanding of aerothermoelastic analysis for hypersonic vehicles.
Excellent organizational and time management abilities
Desire to work both independently and in a team environment as the project requires
Excellent verbal and written communication skills
Proven track record in conducting both applied and fundamental research, evidenced by publications, patents, or successful technology demonstrations.
Ph.D. in Mechanical Engineering, Aerospace Engineering, Materials Science, or a closely related field.
U.S. Citizenship is required

Responsibilities

Develop and implement surrogate models, emphasizing interpolation-based approaches (IROMs) such as neural networks. Investigate methods including residual networks, recurrent models, and neural operators to capture nonlinear and unsteady aerodynamics. Support CFD data generation and evaluate model performance across flight conditions and structural deformations.
Integrate high- and low-fidelity computational data with experimental datasets into a unified framework. Apply hybrid physics/machine learning approaches, including residual learning and layered surrogates, to balance accuracy and efficiency and improve generalization across geometries and operating regimes.
Evaluate model accuracy and efficiency across vehicle configurations and trajectories in coordination with AFRL. Synthesize trends in aerodynamic performance versus deformation and support transition of models into operational environments, including validation, documentation, and participation in technical reviews.