Molex is looking for a Machine Learning Engineer to build physics-informed surrogate models that help engineering teams move faster. This role focuses on using Azure Machine Learning and Azure GPU compute (ND/NC series) to predict simulation outcomes from design parameters, reducing the need to run every full high-fidelity simulation. You will deploy, monitor, and continuously improve models using uncertainty scoring and retraining as new validation results come in.
What you’ll do
- Design and train surrogate models such as neural networks, Gaussian processes, gradient-boosted trees, and GNNs/PINNs using Azure GPU compute.
- Apply physics-informed constraints so predictions remain physically valid, not just statistically accurate.
- Implement model uncertainty and confidence scoring to determine which designs require full simulation validation, then feed results back into the training cycle.
- Deploy and version models through Azure ML endpoints and model registry, with rolling drift monitoring.
- Benchmark surrogate model performance against full simulation to quantify speedup and support platform-level optimization.
What you bring
- Extensive hands-on production ML experience, including building, training, and deploying models (not just integrating pretrained APIs).
- 10+ years building ML for physical and engineering systems, including surrogate modeling, physics-informed ML, or scientific ML.
- Strong Python skills with PyTorch or TensorFlow.
- Working understanding of relevant engineering/physics fundamentals and the simulation data formats for your domain.
- Experience with Azure Machine Learning or a similar cloud ML platform.
- Familiarity with uncertainty quantification, including Bayesian approaches and ensembling.
Tools and technologies
Azure Machine Learning, Azure GPU compute (ND/NC series), Python, PyTorch, TensorFlow, Azure ML endpoints, model registry, neural networks, Gaussian processes, gradient-boosted trees, GNNs, PINNs, Bayesian approaches, ensembling.
Compensation and location
Austin, TX (onsite) · USD 170,000 - 250,000 per year · 10+ years minimum experience.
Benefits
- Medical, dental, and vision
- Flexible spending and health savings accounts
- Life insurance
- ADD
- Disability
- Retirement
- Paid vacation/time off
- Educational assistance
- May also include infertility assistance
- Paid parental leave and adoption assistance
What will put you ahead
- Direct experience with industry-standard EM or physics simulation tools
- Geometric deep learning for CAD data, including graph neural networks and mesh-based models
- Background in RF/high-speed electronics or interconnect design
