Azure ML Physics‑Informed ML Engineer for Fast Design

Molex; Austin (TX); On-site; USD 170,000 - 250,000; Full time

Benefits offered by this job

Medical

Dental

Vision

Flexible spending accounts

Life insurance

ADD

Disability

Retirement

Paid vacation/time off

Educational assistance

Infertility assistance

Paid parental leave

Adoption assistance

Job summary

Molex in Austin, TX is seeking an ML Engineer to build physics-informed surrogate models on Azure ML that predict engineering outcomes from design parameters. You’ll pre-screen candidate designs in milliseconds to accelerate the design-optimization cycle.

You will collaborate with data scientists and MLOps teams to deploy models via Azure ML endpoints, monitor drift, and benchmark speedups versus full simulations to guide platform-level performance tuning.

Qualifications

• Hands-on experience building, training, and deploying ML models in production.
• 10+ years building ML for physical/engineering systems.
• Strong Python with PyTorch or TensorFlow.
• Understanding of engineering/physics fundamentals and simulation data formats.
• Experience with Azure Machine Learning or a similar cloud ML platform.
• Familiarity with uncertainty quantification (Bayesian approaches, ensembling).

Responsibilities

• Design and train surrogate models (neural networks, Gaussian processes, gradient-boosted trees, GNNs/PINNs) on Azure GPU compute (ND/NC series).
• Incorporate physics-informed constraints so predictions stay physically valid, not just statistically fit.
• Build model-uncertainty and confidence scoring to decide which designs need full simulation validation, then retrain as new results arrive.
• Deploy and version models via Azure ML endpoints and model registry; monitor for drift on a rolling basis.
• Benchmark surrogate vs. full-simulation speedup to guide platform-level performance tuning.

Skills

Production ML systems

Physics-informed ML

Python programming

Azure ML experience

Tools

PyTorch

TensorFlow

Job description

Molex in Austin, TX is seeking an ML Engineer to build physics-informed surrogate models on Azure ML that predict engineering outcomes from design parameters. You’ll pre-screen candidate designs in milliseconds to accelerate the design-optimization cycle.

You will collaborate with data scientists and MLOps teams to deploy models via Azure ML endpoints, monitor drift, and benchmark speedups versus full simulations to guide platform-level performance tuning.