Postdoctoral Associate - PNT - SUNY Polytechnic Institute

SUNY Polytechnic Institute • Utica, NY

33d • $60,000 - $65,000

About The Position

The Artificial Intelligence Exploration Center at SUNY Polytechnic Institute invites applications for a Post-Doctoral Associate to research on the generation and analysis of sequential data, particularly in the domain of Positioning, Navigation, and Timing (PNT). The research aims to generate and evaluate the quality of synthetic PNT data created using pre-trained foundation models (FMs) such as Large Language Models (LLMs). The position will also involve creating quantitative evaluation frameworks to assess the quality, realism, and reliability of generated data, as well as integrating graph-based and network analytic approaches, such as visibility graph analysis, to uncover latent patterns, detect anomalies, and characterize dynamical behavior. This position offers an exciting opportunity to work at the intersection of AI, physics, data science, and systems engineering, contributing to the development of robust and verifiable synthetic data pipelines for next-generation analytical and decision-support systems. The successful candidate will join a multidisciplinary research team comprising mathematicians, physicists, engineers, and other faculty members at SUNY Polytechnic Institute. The position is based in Utica, NY.

Requirements

• The successful candidate will hold a doctoral degree in Computer Science, Data Science, Physics, Applied Mathematics, Electrical Engineering, or a closely related field.
• Proficiency in Python/C and familiarity with at least one deep learning framework (e.g., PyTorch, TensorFlow, or Keras).
• Interest in or prior experience with generative AI methods such as GANs, VAEs, transformers, or foundation models (LLMs, TSFMs).
• Ability to design and conduct computational experiments, including model training and evaluation.
• Experience with data analysis, visualization, and quantitative assessment of model outputs.
• Strong communication and writing skills, with an interest in collaborative, interdisciplinary research.

Nice To Haves

• Background in signal processing, network science, or statistical physics applied to time series and/or complex systems analysis.
• Familiarity with PNT data, spatiotemporal datasets, or related domains.
• Experience with graph-based data analysis or anomaly detection methods.
• Exposure to high-performance or GPU-based computing environments.
• Demonstrated ability to contribute to publications or technical reports.

Responsibilities

• Collaborate with the project's Principal Investigators to design and implement generative AI models for sequential PNT data.
• Develop and fine-tune foundation models for synthetic data generation: Time Series Foundation Models, Variational Autoencoders, Generative Adversarial Networks, and Large Language Models (LLMs, TSFMs, VAEs, GANs).
• Design experiments to test synthetic data quality, reliability, and resilience under corrupted or adversarial conditions.
• Participate in compiling and curating large-scale datasets for model training and benchmarking.
• Develop and document analytical tools and quantitative metrics for comparing real and synthetic PNT data.
• Construct network-based representations of time series data to analyze structural and temporal dependencies.
• Contribute to the preparation of publications, technical reports, and conference presentations.
• Engage in proposal writing and outreach activities that expand the project's scope and impact.

Benefits

• healthcare
• dental
• vision
• pension plans
• competitive pay
• generous paid time off
• tuition assistance
• life insurance
• long-term disability insurance

What This Job Offers

• Industry: Educational Services
• Education Level: Ph.D. or professional degree
• Number of Employees: 5,001-10,000 employees