Principal areas of interest include:
Machine learning for bioacoustics, applying state of the art methods for species identification and soundscape modelling.
Optimized sampling design to maximize the spatiotemporal efficiency of surveys.
Improved acoustic data engineering including streamlined model tuning and validation processes and data compression.
Scalable applications of emergent bioacoustic methods such as abundance estimation and individual recognition.
The fellow will be expected to:
Lead in the development of these new capabilities.
Develop and manage partnerships with relevant institutions related to these new technologies including existing collaborations with academic institutions.
Be able to work independently in a variety of remote environments.
Be able to work flexibly and collaboratively with multiple teams across different time-zones.
Provide technical expertise and support grant writing and reporting activities.
Provide mentorship to build capacity of NS and SDZWA young scientists.
To be successful, applicants must have the following expertise:
Demonstrated excellence in applied bioacoustics for scientific research.
Programming proficiency in Python and common packages including Numpy, Pandas, SciKit-Learn, and machine learning frameworks such as PyTorch or TensorFlow.
Applications of acoustic classification algorithms such as PERCH and BirdNET or a strong background in neural networks.
Familiarity with the principles of ecological monitoring and common analytical methods. Applicants with expertise in population or community ecology will be preferred.
Experience using collaborative software tools with rigorous documentation.
Apply via :
airtable.com
