We are currently developing a pipeline for data analysis processes such as automated species tagging and image QA. We are looking for contributors to help develop machine learning models for these processes as well as to help build an infrastructure for our data to be securely processed at scale. Skills that are essential are Python and some exposure to a deep learning libraries like PyTorch or Tensorflow is useful for modeling tasks. Experience with numpy/pandas or SQL are also useful. For those interested in infrastructure, any experience in data science pipeline engineering is useful, with tools like Apache Airflow and Kubernetes of particular use.