Official websites use .gov
A .gov website belongs to an official government organization in the United States.
Secure .gov websites use HTTPS
A lock (
) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.
Bioformulation Digital Twin Developer
This position is part of the National Institute of Standards and Technology (NIST) Professional Research Experience Program (PREP). Individuals appointed through PREP perform technical work supporting collaborative scientific research between NIST and participating academic institutions.
U.S. Citizen Preferred
The Work Will Entail
The associate will develop digital-twin-guided autonomous experimentation methods for soft-material and bioformulation systems. Working with the NIST Autonomous Formulation Laboratory, the associate will combine physics-grounded modeling, generative machine learning, automated formulation preparation, and multimodal characterization to connect formulation conditions, material structure, and measured properties.
The research will focus on computational representations of three-dimensional structure and mesostructure and on virtual instruments that predict experimental observables from those representations. These models will be integrated with automated workflows that select informative experiments, reconcile measurements from multiple techniques, quantify uncertainty, and update the material digital twin. Relevant measurements may include small-angle X-ray and neutron scattering, resonant soft X-ray scattering, cryogenic electron microscopy, light scattering, spectroscopy, rheology, and related methods.
Duties
- Develop, train, and validate generative and physics-informed models for the structure and behavior of soft-material and bioformulation systems.
- Create digital representations that connect formulation composition and processing conditions to material structure and predicted measurement results.
- Develop virtual instruments and inverse-modeling workflows that reconcile multimodal experimental data.
- Integrate digital-twin models with automated formulation and characterization workflows to guide experiment selection and model refinement.
- Incorporate uncertainty quantification, calibration, and validation methods so that computational predictions can be compared rigorously with experimental measurements.
- Define benchmarks for physical plausibility, reproducibility, structural diversity, and agreement with measured data.
- Produce documented code, datasets, metadata, model documentation, protocols, presentations, and peer-reviewed publications.
Required Skills, Expertise, and Qualifications
- Ph.D. completed by the start date in machine learning, computer science, physics, chemistry, materials science, chemical engineering, or a related field.
- Strong Python programming skills and experience with a modern machine-learning framework such as PyTorch, including GPU or high-performance-computing workflows.
- Experience with generative modeling, inverse problems, differentiable physics, probabilistic modeling, or related methods for scientific data.
- Experience with soft matter, self-assembly, colloids, surfactants, polymers, biomaterials, or bioformulations.
- Experience with autonomous experimentation, active learning, Bayesian optimization, laboratory automation, or simulation-to-measurement workflows is desirable.
- Demonstrated ability to conduct independent research, develop reproducible computational workflows, communicate technical results, and collaborate with experimental and computational researchers.
How to Express Interest
Interested persons (U.S. Citizens preferred) who meet all of the required qualifications are invited to express their interest by sending an email that briefly describes their qualifications along with a CV to 642assoc [at] nist.gov (642assoc[at]nist[dot]gov). U.S. Citizens should note “U.S. Citizen” and the opportunity title in the email subject line. All others should note “Non-U.S. Citizen” and the opportunity title in the email subject line.