Digital Twin Scientist: Soft Materials & Bioformulations

National Institute of Standards and Technology; Gaithersburg (MD); On-site; USD 75,000 - 95,000; Full time

Job summary

National Institute of Standards and Technology (NIST) invites applications for an Associate in the PREP program. The role focuses on developing digital-twin-guided autonomous experimentation methods for soft-materials and bioformulations, integrating physics-based modeling with machine learning and automated workflows.

The work connects formulation conditions to material structure and measurable properties, using automated pipelines and multiple techniques to predict observables and guide

Qualifications

• Ph.D. completed by the start date in a relevant field (ML/CS/Physics/Chemistry/Materials Science).
• Strong Python and PyTorch experience with GPU/ HPC workflows.
• Experience with generative modeling, inverse problems, differentiable physics, or probabilistic modeling.

Responsibilities

• Develop, train, and validate generative and physics-informed models for soft-materials and bioformulations.
• Create digital representations connecting composition and processing to structure and predicted measurements.
• Develop virtual instruments and inverse-modeling workflows for multimodal data.
• Integrate digital-twin models with automated formulation and characterization workflows to guide experiments.
• Incorporate uncertainty quantification, calibration, and validation against experimental data.
• Produce documented code, datasets, metadata, and protocols.

Skills

Python

PyTorch

GPU HPC

Generative modeling

Inverse problems

Differentiable physics

Probabilistic modeling

Soft matter

Self-assembly

Colloids

Polymers

Biomaterials

Autonomous experimentation

Active learning

Bayesian optimization

Laboratory automation

Simulation-to-measurement workflows

Education

Ph.D. completed by start date in a relevant field

Tools

High-performance computing workflows

Job description

National Institute of Standards and Technology (NIST) invites applications for an Associate in the PREP program. The role focuses on developing digital-twin-guided autonomous experimentation methods for soft-materials and bioformulations, integrating physics-based modeling with machine learning and automated workflows.

The work connects formulation conditions to material structure and measurable properties, using automated pipelines and multiple techniques to predict observables and guide