2027 Summer Intern – Research and Development – Vehicle Aerodynamics and Machine Learning

Description

You will join the vehicle aerodynamics and machine learning group for a 2027 summer internship, working across physics-based vehicle simulation, CFD, scientific machine learning, and aerodynamic design optimization.

The work uses CFD and AI/ML to reduce drag, improve aerodynamic performance, and speed up design exploration for future vehicles. Tasks can include studying flow fields, building data-driven aerodynamic models, judging design concepts, and turning findings into practical engineering tools.

The role suits a curious student who likes applying engineering fundamentals and modern computational methods to hard problems. You will learn from experienced researchers and engineering partners.

The team sits in the Energy and Propulsion Systems Research group, which does applied work on efficiency, performance, range, cost, and sustainability. It works with researchers, vehicle development groups, universities, technology partners, and industry leaders.

You will work alongside aerodynamicists, CFD specialists, data scientists, ML researchers, vehicle designers, optimization experts, and engineers from propulsion, thermal, body, chassis, and vehicle performance.

Other activities may include innovation challenges, talks with industry leaders, networking events, technical presentations, and community service.

Responsibilities

• Support aerodynamics studies of external flow, drag, lift, downforce, cooling airflow, and efficiency.
• Set up, run, monitor, and post-process CFD simulations for full vehicles and components.
• Prepare geometry, meshes, boundary conditions, design variables, and analysis workflows.
• Analyze aerodynamic coefficients, pressure, velocity fields, wake structures, and other performance metrics.
• Build and curate datasets from simulations, experiments, vehicle geometry, and design variables.
• Develop, train, test, and evaluate machine learning or surrogate models for aerodynamic quantities and flow fields.
• Explore physics-informed, data-driven, reduced-order, graph-based, and other scientific ML methods for vehicle aerodynamics.
• Apply preprocessing, feature engineering, dimensionality reduction, model selection, tuning, and validation.
• Assess model accuracy, robustness, generalization, uncertainty, and limits across geometries and operating conditions.
• Compare ML predictions against CFD, wind-tunnel, experimental, and other trusted engineering results.
• Support design of experiments, surrogate-based optimization, sensitivity studies, and shape exploration.
• Write Python scripts and tools that automate simulation setup, data processing, training, visualization, and reporting.
• Find ways to shorten analysis time and give aerodynamic feedback earlier in vehicle design.
• Document assumptions, methods, data sources, model settings, results, limitations, and recommendations.
• Make plots, visualizations, technical reports, presentations, and demos for engineering and research audiences.
• Work with researchers and partners to frame technical questions, review results, and suggest next steps.
• Present your findings and take part in innovation, networking, and professional development events.

Requirements

• Required: pursuing an MS or PhD in mechanical engineering, aerospace engineering, computational engineering, computer science, applied mathematics, physics, data science, or a closely related technical field.
• Required: able to work full time, 40 hours per week, during the summer months.
• Preferred: coursework, research, or project work in fluid mechanics, vehicle aerodynamics, CFD, turbulence modeling, numerical methods, optimization, or heat transfer.
• Preferred: experience with Python, MATLAB, C++, or a comparable programming language.
• Preferred: experience with NumPy, pandas, SciPy, scikit-learn, PyTorch, TensorFlow, or similar scientific computing and ML libraries.
• Preferred: familiarity with CFD, CAE, CAD, meshing, visualization, Linux, high-performance computing, or engineering software workflows.
• Preferred: experience applying ML to scientific, engineering, physical simulation, or time-series data.
• Preferred: familiarity with surrogate modeling, physics-informed ML, graph neural networks, neural operators, transfer learning, uncertainty quantification, or model explainability.
• Preferred: experience with design of experiments, parameter studies, optimization, or automated engineering workflows.
• Preferred: ability to judge data quality, spot modeling limits, and tell physical results apart from numerical or data artifacts.
• Preferred: experience communicating results through reports, presentations, plots, code documentation, or demos.
• Preferred: strong analytical, written, and verbal communication skills.
• Preferred: able to work independently while collaborating well with researchers and cross-functional engineering teams.

Conditions

The role is hybrid, with reporting to Warren, MI at least three times per week, or at another frequency the business sets.

Start dates are May 24, 2027 and June 14, 2027.

The company does not provide immigration sponsorship for this role. Do not apply if you will need company immigration sponsorship now or later. This covers direct sponsorship, listing the company as immigration employer of record on a government form, and any work authorization that needs a written submission or other company immigration support, such as H1-B, OPT, STEM OPT, CPT, TN, or J-1.

Candidates may be required to complete a role-related assessment and or a pre-employment screening before starting.

The company is committed to an inclusive, discrimination-free workplace.

Benefits

• Well-being support is offered from day one, covering both work and home.
• Total rewards information is available for review.