Deep Learning Postdoctoral Fellow
The Johns Hopkins University Applied Physics Laboratory (APL), a national leader in scientific research and development, located midway between Baltimore and Washington, DC is seeking a Postdoctoral Fellow in the field of Deep Learning applied to Remote Sensing.
Postdoctoral Fellow Candidate will perform leading research in the area of deep learning (transfer learning, convolutional neural networks, machine learning, novel adaptive classification methods, feature extraction, physics models, and statistical signal processing) applied to multi-modal, remote sensing applications.
Duties (Listed in order of importance with the estimated amount of time spent at each task):
- Design, develop, and train novel, deep learning-based, multi-object detection, classification, and tracking algorithms for multi-modal remote sensing and intelligence, surveillance, and reconnaissance (ISR) systems. (50%)
- Extend the state-of-the-art in the area of deep learning systems for remote sensing data (ground, sea, air and/or space-domain imagery and video). (30%)
- Develop and employ low size, weight, and power (SWaP) systems and deep learning methods for real-time onboard image and video processing. (10%)
- Preparation of funding proposals, documents, and reports, to include publishing and presenting in peer-reviewed journals and at relevant conferences. (10%)
Note: This job summary and listing of duties is for the purpose of describing the position and its essential functions at time of hire and may change over time.
PhD in Computer Science, Machine Learning, Computer Vision, Imaging Science, Remote Sensing, or related discipline. Experience developing image/signal processing algorithms, classifiers, and software for remote sensing systems and applications. Experience applying deep learning and pattern recognition methods to remotely sensed data, imagery and video. Experience with automated processing and exploitation of multi-modal, full motion video (FMV) and imagery.
Comfortable training and/or fine-tuning convolutional neural networks (CNNs) using popular deep learning libraries and toolkits. Strong C, C , Matlab, and/or other prototyping and software development skills. Demonstrated ability to publish and communicate technical work in highly-regarded technical journals or other technical forums. The candidate is expected to be self-motivated and able to work collaboratively in a team environment with scientists and engineers representing a variety of different backgrounds, skills, and experience levels. Excellent oral and written communication skills with ability to communicate technically-complex ideas to both scientific and non-scientific audiences.
Proficient in deep learning, machine learning, pattern recognition, object detection, and automated processing of various forms of GEOINT. Prior experience applying deep learning techniques to FMV and IMINT for defense applications. Prior experience with and expertise in SAR, MSI/HSI, and/or 3D/LIDAR systems desired. Experience developing deep learning and machine learning classifiers for multi-GPU and low SWaP platforms, including UAVs and drones of all sizes. Experience designing, training, and employing CNN architectures, RNNs, LSTMs, and transfer learning. Experience in leading developmental teams (5 people) and writing proposals/whitepapers.
Special Working Conditions: This position may require occasional travel for technical meetings with sponsors, conferences, and field testing. Travel is not expected to be more than 5% of the time in any given month on a regular basis.
Security: Applicant selected will be subject to a government security clearance investigation and must meet the requirements for access to classified information. Eligibility requirements include U.S. citizenship.
Benefits: APL offers a comprehensive benefits package including a liberal vacation plan, a matching retirement program, significant educational assistance, a scholarship tuition program for staff with dependents, and competitive salaries commensurate with skills and experience. For more information about our organization, please visit our web site at www.jhuapl.edu.
Equal Employment Opportunity: Johns Hopkins University/Applied Physics Laboratory (APL) is an Equal Opportunity/Affirmative Action employer that complies with Title IX of the Education Amendments Acts of 1972, as well as other applicable laws. All qualified applicants will receive consideration for employment without regard to race, color, religion, sexual orientation, gender identity, national origin, disability, or protected Veteran status.
Back to top