University of California, Los Angeles
Staff Research Associate 3
University of California, Los Angeles, Los Angeles, California, United States, 90079
Overview
The University of California Los Angeles (UCLA) is seeking a highly motivated and creative machine learning scientist with expertise in image segmentation. The selected candidate will work with the PI to implement and parameterize a computer vision deep learning model to classify giant kelp canopy from high resolution satellite imagery. Additional tasks will include developing models to extract sandy beach and dune features from high resolution satellite and drone imagery. Preference will be given to candidates who have demonstrated creative approaches to analyzing remote sensing data of coastal ecosystems. The successful candidate should have strong quantitative skills, proficiency in standard programming languages (Python, Matlab), proficiency in deep learning and computer vision tools (PyTorch, Tensorflow, OpenCV, Open3D), excellent written and oral communication skills, and interest in publication of the results of the research. This position is primarily remote; however the research associate will need to collaborate frequently with the faculty supervision.
Responsibilities
Implement and parameterize a computer vision deep learning model to classify giant kelp canopy from high resolution satellite imagery.
Develop models to extract sandy beach and dune features from high resolution satellite and drone imagery.
Collaborate with the PI and faculty supervision and contribute to publication of research results.
Qualifications
5 Years+ Minimum of 5 years of relevant postgraduate experience in building and deploying computer vision deep learning models. (Required)
Strong background in environmental remote sensing. (Required)
Experience with managing large data sets and interpreting multiple data formats, such as netCDF, geotiffs, etc. (Required)
Demonstrated advanced knowledge of programming with C++, Python and/or Matlab. (Required)
Demonstrated advanced knowledge of deep learning and computer vision packages including PyTorch, Tensorflow, OpenCV, and/or Open3D. (Required)
Experience in model testing and validation. (Required)
Excellent oral and written communication skills to communicate effectively and professionally with people at multiple institutions. (Required)
Experience writing, editing, and revising journal articles and documentation. (Required)
Education
Bachelor's Degree in Geography, Environmental Science, Engineering, Computer Science, or a related discipline and/or equivalent experience / training. (Required) And
Special Conditions for Employment
Background Check: Continued employment is contingent upon the completion of a satisfactory background investigation.
Live Scan Background Check: A Live Scan background check must be completed prior to the start of employment.
Schedule Variable
Union/Policy Covered RX-Research Support Professionals
Notes Complete Position Description
Note: For more details, the original posting included a link to the UC market pay job listing; links have been removed in this refined description to maintain a clean, accessible format.
#J-18808-Ljbffr
The University of California Los Angeles (UCLA) is seeking a highly motivated and creative machine learning scientist with expertise in image segmentation. The selected candidate will work with the PI to implement and parameterize a computer vision deep learning model to classify giant kelp canopy from high resolution satellite imagery. Additional tasks will include developing models to extract sandy beach and dune features from high resolution satellite and drone imagery. Preference will be given to candidates who have demonstrated creative approaches to analyzing remote sensing data of coastal ecosystems. The successful candidate should have strong quantitative skills, proficiency in standard programming languages (Python, Matlab), proficiency in deep learning and computer vision tools (PyTorch, Tensorflow, OpenCV, Open3D), excellent written and oral communication skills, and interest in publication of the results of the research. This position is primarily remote; however the research associate will need to collaborate frequently with the faculty supervision.
Responsibilities
Implement and parameterize a computer vision deep learning model to classify giant kelp canopy from high resolution satellite imagery.
Develop models to extract sandy beach and dune features from high resolution satellite and drone imagery.
Collaborate with the PI and faculty supervision and contribute to publication of research results.
Qualifications
5 Years+ Minimum of 5 years of relevant postgraduate experience in building and deploying computer vision deep learning models. (Required)
Strong background in environmental remote sensing. (Required)
Experience with managing large data sets and interpreting multiple data formats, such as netCDF, geotiffs, etc. (Required)
Demonstrated advanced knowledge of programming with C++, Python and/or Matlab. (Required)
Demonstrated advanced knowledge of deep learning and computer vision packages including PyTorch, Tensorflow, OpenCV, and/or Open3D. (Required)
Experience in model testing and validation. (Required)
Excellent oral and written communication skills to communicate effectively and professionally with people at multiple institutions. (Required)
Experience writing, editing, and revising journal articles and documentation. (Required)
Education
Bachelor's Degree in Geography, Environmental Science, Engineering, Computer Science, or a related discipline and/or equivalent experience / training. (Required) And
Special Conditions for Employment
Background Check: Continued employment is contingent upon the completion of a satisfactory background investigation.
Live Scan Background Check: A Live Scan background check must be completed prior to the start of employment.
Schedule Variable
Union/Policy Covered RX-Research Support Professionals
Notes Complete Position Description
Note: For more details, the original posting included a link to the UC market pay job listing; links have been removed in this refined description to maintain a clean, accessible format.
#J-18808-Ljbffr