DEVCOM Army Research Laboratory
Just Landed
New Today
Faculty Fellowship for AI Model Optimization Research for Inference Acceleration in Edge Computing Environments DEVCOM Army Research Laboratory in United States
Degree Level
Postdoc
Field of study
Computer Science
Funding
Available
Country
United States
University
DEVCOM Army Research Laboratory
Apply for this position
Keywords
Suggested positions
About this position
This faculty fellowship at the DEVCOM Army Research Laboratory focuses on AI model optimization for inference acceleration in edge computing environments. The project aims to develop theoretical and experimental approaches for accelerating inference on resource-constrained heterogeneous edge platforms, with an emphasis on predicting optimal model architectures through neural network architecture search.
The research spans both convolutional neural networks and large language models, with the goal of improving how these models perform when deployed close to the edge. A major part of the work is understanding the trade-offs among accuracy, latency, and compression in optimized AI models, and then using that understanding to guide better model design and deployment choices.
The fellowship also explores state-of-the-art approaches such as quantization, model pruning, and other methods for reducing computational complexity in order to make AI inference faster and more efficient on constrained platforms. In addition, the project calls for mathematical foundations that can support the optimization process, help ensure convergence to optimal solutions, and satisfy all relevant constraints.
Another theme is the development of layer-wise gradual optimization approaches, suggesting a detailed and structured path to improving model efficiency step by step. The work is situated within ARL’s Network Cyber & Computational Sciences research area, in an environment oriented toward distributed analytics, secure resilient communication networks, and Army-relevant scientific and technical capabilities.
The named advisor for the opportunity is Venkateswara Dasari at ARL.
Funding details
Available
What's required
Citizenship must be U.S. Citizen only. Applicants must hold a doctoral degree, with the opportunity open to doctoral degree holders at faculty level or with 5+ years of experience as a senior fellow. A complete application requires a CV or resume, three reference forms, and transcripts verifying receipt of degree; a student or unofficial copy is acceptable. If selected by an advisor, the participant must also prepare a research proposal aligned with a specific ARL opportunity, with a clear objective, defined outcome, planned direction, expected completion period, brief background, and references to prior published work where useful.
How to apply
Apply through the Zintellect application portal using the opportunity link. Submit your CV or resume, three references, and transcripts with the application. If selected by an advisor, prepare and submit the required research proposal to the ARL-RAP review panel.
Make your next move.
Prepare your application
Review drafts and confirm requirements with the university.
Make your next move.
Prepare your application
Review drafts and confirm requirements with the university.