Work onsite in Lisle, IL to accelerate engineering design cycles by delivering physics-informed machine learning surrogates on Azure.

Design and train surrogate models, including neural networks, Gaussian processes, gradient-boosted trees, and GNNs/PINNs
Train on Azure GPU compute using ND/NC series resources
Apply physics-informed constraints to keep predictions physically valid, beyond purely statistical fit
Create model-uncertainty and confidence scoring to determine which candidate designs require full simulation validation
Retrain surrogate models as new simulation results become available
Deploy and manage model lifecycle using Azure ML endpoints and model registry
Monitor deployed models for drift on a rolling basis
Benchmark surrogate runtime versus full simulation to guide platform-level performance tuning
Partner with data scientists and MLOps teams to productionize and operationalize model workflows

Extensive hands-on experience building, training, and deploying ML models in production (not limited to pretrained API usage)
10+ years building ML for physical or engineering systems, including surrogate modeling and physics-informed or scientific ML
Strong Python experience with PyTorch or TensorFlow
Understanding of engineering/physics fundamentals and relevant simulation data formats in your domain
Experience with Azure Machine Learning or a similar cloud ML platform
Familiarity with uncertainty quantification, including Bayesian approaches and ensembling

Direct experience with industry-standard EM or physics simulation tools
Geometric deep learning experience, including graph neural networks and mesh-based models for CAD data
Background in RF/high-speed electronics or interconnect design

Location: Lisle, IL 60532 (onsite)

Compensation: USD 170,000 - 250,000 per year

Experience: 10+ years

Machine Learning Engineer

Job Description