Machine Learning Engineer

What you'll do

• Develop and deploy surrogate, reduced-order, and physics-informed ML models to accelerate multiphysics simulations.
• Build ML pipelines for training, validation, uncertainty quantification, and refinement using experimental and simulation data.
• Integrate models into Digital Twin systems and develop anomaly detection, diagnostics, and autonomous optimization capabilities.

What they ask for

• Master's or PhD in Machine Learning, Computational Physics, Applied Mathematics, Data Science, Computer Science, or a closely related field.
• Experience building, training, and deploying ML models for complex physical systems; knowledge of deep learning, probabilistic models, and uncertainty quantification.
• Expert-level Python and experience with HPC environments, including batch schedulers and MPI/OpenMP parallelization.
• Experience with PDE-based simulation outputs, scientific ML pipelines, and Gaussian processes, neural network surrogates, reduced-order models, or equivalent metamodeling techniques.

Nice to have

• Experience with PINNs or neural operators, or background in laser physics, plasma physics, high-energy-density science, or related domains.
• Experience with digital twin platforms, multidisciplinary design optimization, reinforcement learning, Monte Carlo methods, or scientific MLOps tooling.

Tools

Python, C++, Fortran, PyTorch, TensorFlow/JAX, COMSOL, ANSYS, MPI/OpenMP

AI focus

Develop physics-informed ML, surrogate and reduced-order models, active learning, Bayesian optimization, anomaly detection, predictive diagnostics, and reinforcement-learning-based control for fusion-system simulations and Digital Twins.