Optimization of DNN based computer vision algorithms for resource constrained tactical edge

ORAU; Aberdeen (MD); On-site; USD 80,000 - 120,000; Full time

Job summary

ORAU is seeking a candidate to optimize and profile computer vision algorithms for deployment on edge computing devices in Aberdeen, Maryland. The ideal applicant should hold a Master's or Doctoral Degree in Engineering or a related field and have experience with deep learning and algorithm optimization techniques. Responsibilities include benchmarking algorithms, designing a model-switching framework, and working closely with partners to meet project goals.

Qualifications

• Citizenship: U.S. Citizen only.
• Experience with computer vision, deep learning, and edge computing.
• Knowledge of algorithm optimization techniques for constrained devices.

Responsibilities

• Profile and benchmark computer vision algorithms on edge hardware.
• Optimize algorithm performance for resource constraints.
• Design and implement a model-switching framework for dynamic model loading.
• Collaborate with internal and external partners to advance project goals.

Skills

Computer vision

Deep learning

Algorithm optimization

Analytical skills

Education

Master’s Degree in Engineering or related field

Doctoral Degree in Engineering or related field

Job description

About the Research

Objection detection and semantic segmentation-based computer vision algorithms are essential for visual scene understanding on tactical edge computing devices. These algorithms typically rely on complex deep neural network architectures that are computationally intensive and not optimized for resource-constrained edge platforms. In this role, you will profile several computer vision algorithms and optimize them for deployment on edge computing platforms with limited resources. You will also develop a generalized model‑switching framework for dynamic loading of models to balance resource constraints with mission requirements.

Responsibilities

• Profile and benchmark computer vision algorithms on edge hardware.
• Optimize algorithm performance for resource constraints.
• Design and implement a model‑switching framework for dynamic model loading.
• Collaborate with internal and external partners to advance project goals.

Qualifications

• Citizenship: U.S. Citizen only.
• Degree: Master’s Degree or Doctoral Degree in Engineering or related field.
• Experience with computer vision, deep learning, and edge computing.
• Knowledge of algorithm optimization techniques for constrained devices.
• Strong analytical and problem‑solving skills.