"NIWC - Graduate Student - Shipboard Scene Understanding Detection and Identification of Objects (SSUDIO) Project (Task 56-1125079)"

Overview

The hourly rate for this position is $22.39 per hour and is non-negotiable.

Graduate Level 1 or above: Pursuing a Master's Degree or PhD in Computer Science, Electrical Engineering, Applied Mathematics, Data Science, or a related major

Under direction, incumbents must have course work in the discipline requested on the task order Statement of Work.

This Statement of Work covers the need for graduate student services to provide technical and/or analytical support in the field of computer science and electrical engineering for a computer vision team, specifically for the Shipboard Scene Understanding Detection and Identification of Objects (SSUDIO) project. The purpose of this project is to develop scene understanding from 3D scans of ships by applying machine learning/computer vision techniques. Additionally, the hired student will assist in corrosion/surface defect detection, object tracking of moving targets, and other machine learning based tasks.

The computer vision team develops solutions for a range of vision tasks via machine learning and deep learning algorithms. The SSUDIO project aims to identify various objects of interest from shipboard 3D scans by training computer vision algorithms to detect, localize, and classify objects.

Responsibilities

The student contractor shall provide support in the following areas, as specified under individual task orders, to the work sponsor:

Performance Requirements:

• Developing and maintaining computer programs using Python and other programming languages to support computer vision and machine learning projects.
• Researching, developing, and improving machine learning workflows and applications.
• Utilizing neural networks and deep learning for object classification/detection/segmentation, Optical Character Recognition, and text localization.
• Completing data labeling tasks for machine learning models, including file and data format conversions. Annotating data, including but not limited to text transcription, classification, and object detection in 2D, 3D, and other data types.
• Conducting research, writing reports/publishing conference papers, and creating demonstrations/visualizations to support the understanding of the algorithms and the data.
• Monthly Status Reports and Bi-Weekly Time Reports shall be in accordance with basic contract CORL.

Qualifications

MINIMUM QUALIFICATIONS

• Graduate Level 1 or above: Pursuing a Master's Degree or PhD in Computer Science, Electrical Engineering, Applied Mathematics, Data Science, or a related major
• Functional knowledge of Python and common libraries (e.g. comfortable with writing functions, classes, loops, etc. and using Anaconda or Python virtual environments)
• Proven oral/written communication skills and documentation habits

Desired Qualifications Requirements:

• Familiarity with Computer Vision or Machine Learning and relevant frameworks ( e.g., Pytorch and/or TensorFlow)
• Familiarity with neural networks and deep learning
• Experience with object classification/detection/segmentation, Optical Character Recognition, or text localization
• Experience with LiDAR and point clouds or other 3D work
• Comfortable working in a Linux environment
• Experience with GIT/source control

ADDITIONAL APPLICANT INFORMATION:

• This position may require the employee to obtain and maintain a DoD security clearance.
• Due to the regulations established by the Department of Defense, only US Citizens may qualify.
• This is a student position and is limited to working 20 hours per week.
• Possible travel to conferences to present research papers and results.
• The student will work remotely most of the time and occasionally on-site.
• This position will remain open until filled.
• Candidate must reside in California and live within a commutable distance from SDSU at time of hire.
• Job offer is contingent upon satisfactory clearance based on background check results (including a criminal record check).