CSIRO Postdoctoral Fellowship in Deep-learning to Detect Anomalous Behaviour in Fisheries 


The Opportunity
  • Do you have an interest in machine learning and marine or fisheries science?
  • Work with World-leading scientists to search for rare and anomalous events
  • Join CSIRO - Australia's premier science and technology research organisation 


CSIRO Early Research Career (CERC) Postdoctoral Fellowships provide opportunities to scientists and engineers who have completed their doctorate and have less than three years of relevant postdoctoral work experience.  These fellowships aim to develop the next generation of future leaders of the innovation system.

In this position you will undertake research in deep learning-based video analysis for detecting rare and anomalous events and behaviours in fisheries. As the successful candidate you will contribute to developing detection and identification algorithms based on a range of data including, on-board video of fishing operations, and vessel transponder data, with the goal of implementing the software in an operational capacity.

Your duties will include:
  • Developing general methods to automate the analysis of imagery and video, addressing problems of lack of labelled data, and developing models to detect anomalous events and behaviour in large-scale datasets. 
  • Implementing these methods efficiently using programing tools such as PyTorch and TensorFlow.
  • Carrying out evaluation of the developed software.
  • Interpret and present research findings in computer vision and machine learning to research scientists and practitioners from a wide range of other scientific areas.

Location:  Hobart TAS
Salary:  AU$86k – AU$94k plus up to 15.4% superannuation
Tenure:  Specified term of 3 years
Reference:  67869

To be considered you will need:
  • A doctorate (or will shortly satisfy the requirements of a PhD) in Platform-relevant discipline area, such as computer vision, machine learning, artificial intelligence or computer science. Please note: To be eligible for this role you must have no more than 3 years (or part-time equivalent) of postdoctoral research experience.
  • A history of professional and respectful behaviours and attitudes in a collaborative environment.
  • Solid knowledge of computer vision and machine learning, and the ability to understand and develop mathematically-founded algorithms and their development in toolkits such as TensorFlow or PyTorch.
  • Demonstrated experience in conducting research and development activities in image and video analysis, computer vision, more specifically in the area of machine learning based image/video analysis for object detection, classification and tracking.

For full details about this role please view the Position Description

Eligibility

The successful applicant will be required to obtain and provide a National Police Check or equivalent.

Applicants must be Australian/New Zealand citizens, Australian permanent residents or Australian temporary residents currently residing in Australia and be able to commence in the role by December 2020/January 2021.

Flexible Working Arrangements

We work flexibly at CSIRO, offering a range of options for how, when and where you work. Talk to us about how this role could be flexible for you. Balance

Diversity and Inclusion

We are working hard to recruit diverse people and ensure that all our people feel supported to do their best work and feel empowered to let their ideas flourish. Diversity and Inclusion Strategy

We are committed to the safety and wellbeing of all children and young people.

About CSIRO

At CSIRO, Australia's national science agency, we solve the greatest challenges through innovative science and technology.

Join us and start creating tomorrow today!

How to Apply

Please apply on-line and provide a cover letter and CV. The cover letter should highlight your interest in the role and address your suitability against each of the selection criteria.

Applications Close

Wednesday 05 August 2020, 11:00 pm AEST

Please click here to apply