ECE Postdoctoral Fellow

Stevens Institute of Technology • Hoboken, NJ

2d • $53,000 - $55,000

About The Position

We are seeking a highly motivated Postdoctoral Fellow to conduct research in machine learning and neural network architecture design, with a focus on computational efficiency, robustness, and reliability in constrained environments. The successful candidate will work on the development and evaluation of robust classifiers, building upon our novel Pseudo-Invertible Neural Networks layers Responsibilities Conduct Innovative Research: The postdoctoral fellow will be responsible for conducting cutting edge research in developing novel robust classifier architectures, with an emphasis on robustness · Design and implement computationally efficient neural network architectures for robust classification · Develop and evaluate Psi-NN-based models that enable classifiers to function as autoencoders without additional decoder networks · Conduct experiments, analyze results, and benchmark performance under computational constraints · Collaborate with faculty, graduate students, and research staff · Publish research findings in peer-reviewed journals and conferences · Mentor graduate and undergraduate researchers as appropriate

Requirements

• Ph.D. in Electrical Engineering, Computer Engineering, Computer Science, or a closely related field
• Strong background in machine learning and neural networks
• Familiarity with pseudo-invertible network architecture (Psi-NN)

Nice To Haves

• Experience with PyTorch for deep learning research and experimentation
• Familiarity with autoencoders, inverse or bidirectional models, robustness, or adversarial learning
• Experience designing or optimizing models for computational efficiency or resource-constrained environment

Responsibilities

• Conduct Innovative Research: The postdoctoral fellow will be responsible for conducting cutting edge research in developing novel robust classifier architectures, with an emphasis on robustness
• Design and implement computationally efficient neural network architectures for robust classification
• Develop and evaluate Psi-NN-based models that enable classifiers to function as autoencoders without additional decoder networks
• Conduct experiments, analyze results, and benchmark performance under computational constraints
• Collaborate with faculty, graduate students, and research staff
• Publish research findings in peer-reviewed journals and conferences
• Mentor graduate and undergraduate researchers as appropriate

What This Job Offers

• Education Level: Ph.D. or professional degree
• Number of Employees: 501-1,000 employees