Overview
Sr. AI/ML Research Engineer to build next-generation physics-based AI capabilities for fluid and thermal systems, enabling faster and more accurate simulation and decision-making.
What you'll do
- Develop AI/ML methods for CFD and multi-physics simulation problems in areas like fluid flow and heat transfer.
- Build physics-informed neural networks and scientific ML approaches for forward/inverse problems and parameter estimation.
- Create surrogate and reduced-order models to accelerate high-fidelity simulation while preserving accuracy.
- Apply Design of Experiments methods to simulation campaigns and sensitivity analysis.
- Work with structured/unstructured simulation data from solvers such as ANSYS Fluent, STAR-CCM+, and OpenFOAM.
- Design training, validation, and benchmarking workflows using simulated and experimental datasets.
- Partner with domain experts and product teams to deploy research into usable workflows.
What you'll need
- PhD or MTech in Mechanical Engineering, Aerospace Engineering, Applied Mathematics, Computer Science, Physics, or a closely related field with strong CFD/computational science emphasis.
- Strong foundation in computational fluid dynamics, numerical PDE methods, turbulence modeling, and heat transfer.
- Demonstrated experience applying physics-informed neural networks or related methods to engineering/scientific computing.
- Strong Python programming skills and experience with scientific ML frameworks such as PyTorch, TensorFlow, or JAX.
- Experience building end-to-end ML workflows including data preparation, training, evaluation, hyperparameter tuning, and deployment.
- Experience working in Linux and HPC environments, including parallel computing and GPU-based training (desirable).
- Strong understanding of model verification, validation, uncertainty, and physical consistency.
Nice to have
- Experience with neural operators, operator learning, graph neural networks, geometric deep learning, differentiable simulation, or hybrid physics-ML modeling.
- Experience integrating AI models with CFD solvers, optimization frameworks, or digital twin platforms.
- Knowledge of Design of Experiments, design optimization, Bayesian optimization, inverse design, or control for thermal-fluid systems.
- Familiarity with geometry/mesh pipelines, simulation automation, workflow orchestration, and Moldflow-style workflows.
- Track record of publications, patents, or production deployments in scientific ML, CFD, or physics-based AI.
