Postdoctoral Researcher (Machine Learning)

Job Title

Postdoctoral Researcher (Machine Learning)

Agency

Prairie View A&M University

Department

Department Of Computer Science

Proposed Minimum Salary

Commensurate

Job Location

Prairie View, Texas

Job Type

Staff

Job Description

We invite applications for a highly motivated Postdoctoral Researcher to join our interdisciplinary research team advancing machine learning applications in hyperspectral image analysis and plant science. This position focuses on developing, implementing, and optimizing advanced machine learning and deep learning models that integrate spatial and spectral information to improve photosynthetic pigment identification in data obtained from Hyperspectral Confocal Fluorescence Microscopy (HCFM).

The successful candidate will contribute across the full machine learning research aspects, including but not limited to data engineering, data preprocessing, model design, algorithm development, benchmarking, and scientific communication. The position includes opportunities for leadership, mentoring, and project coordination, including supervision of students, participation in proposal development, and contributions to intellectual property and patent applications.

This position is funded by restricted funds or a grant. Continued employment is contingent upon the renewal of restricted or grant funds.

The salary is determined in accordance with the University’s compensation structure and will be commensurate with the candidates’ education and experience, within the assigned salary range for this position.

Responsibilities:

• Develop, test, and optimize machine learning and deep learning models for hyperspectral plant imaging, including CNNs, UNets, ResNets, DenseNets, Vision Transformers, Autoencoders and Variational Autoencoders, Generative Adversarial Networks, and Graph Neural Networks.

• Improve traditional spectral only analysis methods used in Multivariate Curve Resolution (MCR) by applying approaches that use both spatial and spectral information.

• Process, clean, and curate hyperspectral data collected with HCFM microscopes, and develop reproducible data processing and workflow tools.

• Explore alternative algorithms and data driven approaches to enhance pigment localization and pigment classification accuracy.

• Maintain clear documentation of model architecture, workflows, code, experiments, and results.

• Provide leadership within the research group by taking ownership of project components and mentoring junior researchers.

• Supervise undergraduate and graduate students in machine learning concepts, data analysis, experimental planning, and scientific writing.

• Train new group members on computational tools, machine learning best practices, and research methodologies.

• Assist the principal investigator with the preparation and submission of manuscripts, patent applications, and research proposals.

• Present research outcomes at internal meetings, seminars, conferences, and collaborative review sessions.

• Participate in departmental or college-wide events, committees, and performs other duties as assigned.

Required Education and Experience:

• Ph.D. degree in Computer Science, Electrical or Computer Engineering, Data Science, Computational Biology, Applied Mathematics, or a related discipline.

• At least one year of experience applying machine learning or data driven methods in research settings.

Required Knowledge, Skills, and Abilities:

• Strong programming skills in Python and experience with machine learning libraries such as PyTorch, TensorFlow, scikit learn, and Keras.

• Knowledge of machine learning, deep learning, data analytics, and model evaluation.

• Experience with data processing pipelines, statistical analysis, and data visualization tools including matplotlib, seaborn, and Plotly.

• Strong written and verbal communication abilities and the ability to collaborate with multidisciplinary teams.

• A record of contributing to peer reviewed publications.

Preferred Qualifications:

• Two or more years of experience applying machine learning to scientific imaging or engineering data.

• Familiarity with image processing or hyperspectral imaging, preferably using HCFM or sim