Postdoctoral Fellow; PREP

PREP Research Associate

This position is part of the National Institute of Standards (NIST) Professional Research Experience (PREP) program. NIST recognizes that its research staff may wish to collaborate with researchers at academic institutions on specific projects of mutual interest, thus requires that such institutions must be the recipient of a PREP award. The PREP program requires staff from a wide range of backgrounds to work on scientific research in many areas.

Employees in this position will perform technical work that underpins the scientific research of the collaboration.

The associate will support NIST Community Resilience research by developing methods to standardize, integrate, and analyze heterogeneous field data used to characterize infrastructure, community conditions, and resilience outcomes. The work will focus on creating consistent data structures, metadata, data dictionaries, quality-control procedures, and reproducible computational workflows that allow data collected across field studies, communities, and time periods to be compared and combined.

Data may include mobile or fixed sensor measurements, time-series data, accelerometer and gyroscope measurements, GPS or other geospatial information, infrastructure observations, surveys, interviews, and other qualitative records. The associate will also investigate machine-learning and natural-language-processing methods for extracting entities, relationships, and causal information from field and interview data and linking those representations with quantitative measurements. The research will contribute to field-data collection strategies, interoperable data products, analytical prototypes, technical documentation, reports, and presentations for NIST researchers and external collaborators.

• Develop and evaluate standardized schemas, metadata elements, controlled vocabularies, data dictionaries, provenance records, and quality-control rules for multimodal community resilience field data, including sensor, geospatial, infrastructure, survey, and interview data.
• Design reproducible workflows to ingest, clean, validate, synchronize, link, transform, and version heterogeneous data sources, with particular attention to integrating time-series sensing and location data with contextual or qualitative information.
• Support the design and analysis of field-data collection activities, including mobile or smartphone-based sensing and infrastructure monitoring using measurements such as acceleration, angular motion, location, sound, or related environmental and operational signals.
• Develop and test statistical, machine-learning, and natural-language-processing methods to classify observations and extract entities, relationships, and causal structures from unstructured records such as interviews or transcripts, and connect these outputs to structured field datasets.
• Develop research software or analytical prototypes, communicate findings in internal and stakeholder meetings and technical publications, and ensure that datasets, code, protocols, model outputs, and documentation are reproducible and archived for use by the larger NIST research program.

• A PhD degree, or current PhD candidacy with all degree requirements completed except the dissertation (all-but-dissertation/ABD), in Computational Science, Data Science, Computer Science, Engineering, Applied Mathematics, Systems and Control, or a closely related field.
• Three or more years of relevant research or professional experience applying computational methods to heterogeneous scientific, engineering, infrastructure, transportation, or field-collected data.
• Demonstrated experience with multimodal sensing or time-series data, preferably including accelerometer, gyroscope, GPS/geospatial, acoustic, smartphone, or related field measurements used for infrastructure or transportation monitoring.
• Experience developing machine-learning or statistical methods for classification, inference, data fusion, or pattern discovery across heterogeneous data sources, together with the ability to prototype reproducible data-processing and analysis workflows.
• Experience with natural-language processing or language-model-based methods for entity and relation classification, information extraction, causal-model extraction, or analysis of interviews, transcripts, or other unstructured text is highly desirable.
• Proficiency with programming and scripting tools used in computational research, along with familiarity with version control, reproducible research practices, structured documentation, and collaborative software or data workflows.
• Strong oral and written communication skills demonstrated through interdisciplinary research collaboration, technical presentations, publications, workshops, or mentoring, and the ability to work effectively with NIST researchers…