Postdoctoral Fellow: AI/ML & Uncertainty for PFAS Spectra

Johns Hopkins University; Baltimore (MD); On-site; USD 65,000 - 90,000; Full time

Job summary

Johns Hopkins University in Baltimore seeks a PREP Research Associate to collaborate with NIST PREP staff on PFAS property and spectra modeling. The role blends mathematics, statistics, and data science to develop AI/ML methods with uncertainty quantification across chemistry and physics data.

You will develop algorithms in Python or R, test model performance, and communicate results at seminars and conferences. A strong quantitative background and cross-disciplinary collaboration are essential.

Qualifications

• Advanced degree in a scientific, mathematical or statistical field.
• Experience with applied science and numerical work.
• Ability to work with a multi-disciplinary research team.
• Strong oral and written communication skills.

Responsibilities

• Develop novel algorithms for predicting physical and chemical properties, infrared and mass spectra, and ionization cross sections using experimental and computational data.
• Implement algorithms to study the performance of classification models.
• Assess uncertainty in predictions and classifications from quantum chemistry and physics calculations/simulations.
• Test models computationally with respect to accuracy and uncertainty quantification.
• Develop software to implement the goals stated above (likely in Python or R).
• Disseminate results through posters/seminars at international meetings and university seminars.
• Ensure all results, data, and software are archived and transmitted appropriately.

Skills

Familiarity with applied science & чис

Multidisciplinary collaboration

Oral and written communication

Education

Advanced degree in scientific/mathematical/statistical area

Job description

Johns Hopkins University in Baltimore seeks a PREP Research Associate to collaborate with NIST PREP staff on PFAS property and spectra modeling. The role blends mathematics, statistics, and data science to develop AI/ML methods with uncertainty quantification across chemistry and physics data.

You will develop algorithms in Python or R, test model performance, and communicate results at seminars and conferences. A strong quantitative background and cross-disciplinary collaboration are essential.