USAISR Artificial Intelligence/Machine Learning Postdoctoral Fellowship

Oak Ridge Institute for Science and Education; Frederick (MD); On-site; USD 60,000 - 90,000; Full time

Job summary

Oak Ridge Institute for Science and Education is seeking a post-doctoral fellow to join the U.S. Army Medical Research and Development Command in Frederick, Maryland. The ideal candidate will engage in research projects focusing on advanced modeling techniques, including Discrete Event Simulation and deep learning.

This position offers an opportunity to work on innovative projects in synergy with data scientists and engineers, addressing complex operational challenges within medical research. Candidates should have a PhD in a relevant field and experience in simulation and machine learning.

Qualifications

• Experience with Discrete Event Simulation techniques.
• Strong background in deep learning and neural networks.
• Proficiency in machine learning and computer vision approaches.

Responsibilities

• Design and implement simulation models for complex workflows.
• Develop deep learning architectures for predictive maintenance.
• Train models for extracting information from medical imagery.

Skills

Discrete Event Simulation (DES)

Deep learning architectures

Physics-Informed Neural Networks (PINNs)

Deep Reinforcement Learning (DRL)

Generative Adversarial Networks (GANs)

Bayesian networks

Computer vision

Education

PhD in relevant field

Job description

Description

The Department of Defense (DoD) is offering a post‑doctoral fellowship at the U.S. Army Medical Research and Development Command – Institute of Surgical Research (USAMRDC ISR) within the Expeditionary Medical Systems (EMS) Department. The Selected Candidate will engage with Data Scientists and Systems Engineers in research projects emphasizing advanced modeling techniques.

Projects may involve:

• Designing and implementing Discrete Event Simulation (DES) models to simulate complex system workflows, queuing networks, logistics, and operational state changes within the digital twin environment.
• Developing deep learning architectures for time‑series forecasting, anomaly detection, and predictive maintenance of the physical asset.
• Designing and training Physics‑Informed Neural Networks (PINNs) and hybrid models that respect physical laws governing real‑world systems.
• Applying Deep Reinforcement Learning (DRL) algorithms to optimize processes within simulation environments.
• Utilizing Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and diffusion models to augment sparse datasets and simulate edge‑case operational and clinical scenarios.
• Implementing Bayesian networks and uncertainty quantification techniques to account for sensor noise and model confidence limits.
• Designing, training, and fine‑tuning computer vision models to extract clinically relevant information from medical imagery, video feeds, and operational sensor streams.
• Building and integrating multi‑modal models that fuse vision, text, audio, physiological signals, and structured telemetry to support{