Grant-Funded Researcher (B / C) – Class Hierarchies

Adelaide, Australia
$102,952 to $121,779 or (Level C) $125,537 to $144,368 per annum
03 Feb 2023
End of advertisement period
19 Mar 2023
Contract Type
Fixed Term
Full Time

(Level B) $102,952 to $121,779 or (Level C) $125,537 to $144,368 per annum plus an employer contribution of up to 17% superannuation may apply.

There is one 2-year fixed-term position available, with the possibility of an extension, subject to project end-date. Flexible work arrangements can be negotiated with the right candidate.

Be part of the Australian Institute for Machine Learning – the largest computer vision and machine learning research group in Australia and contribute to world leading Augmented Reasoning research projects

AIML is Australia’s leading research institute in machine learning and artificial intelligence. AIML’s computer vision research is among the best in the world. With world-leading researchers, modern facilities and an innovative culture, we’re committed to delivering research that is highly valued by our local and global communities. Located at Lot Fourteen, Adelaide, AIML is the largest computer vision and machine learning group in Australia with more than 170 members including academics, research staff, and students. The institute works on a mixture of fundamental and commercially oriented research projects in computer vision and machine learning. Find out more at

The Centre for Augmented Reasoning (CAR) is a $20M investment by the (then) Department of Education, Skills and Employment in people and research to make computers better at interacting with humans so that all technology is easier and safer to use. Managed under AIML, the Centre is supporting Advanced Reasoning research through grants and PhD scholarships, facilitating innovation and rapid commercialisation, and increasing AI literacy and engagement in Australia.

The postdoctoral researcher for Extending and exploiting class hierarchies in deep learning will be supervised by Dr Jack Valmadre. The role will contribute to the centre’s objective to progress deep learning and related machine learning research.

This project proposes to investigate the use of hierarchical structures over classes to endow models with knowledge of the world. This will enable models to leverage class relationships during learning and to fail more gracefully in deployment.

Research directions of particular interest include:

  • Extension of existing methods to directed acyclic graphs (DAGs)
  • Development of novel loss functions and training strategies
  • Long-tail and class-imbalanced learning, where tail classes can achieve better representation via their super-classes
  • Representation learning and transfer learning (including few-shot problems), where hierarchies may be used to structure the feature space and avoid neural collapse
  • Open-set recognition, where superclasses provide the ability to recognise unseen objects using more general categories
  • Object detection and tracking, where objects can be detected and associated despite uncertainty of their precise class.

Hierarchical classification has application in numerous domains, including healthcare (disease classification from images, audio or other sensory data), conservation (animal and plant classification using taxonomies), robotics (classification of land vehicles, ships or aircraft). The project will therefore develop a toolkit for evaluating and training models with class hierarchies.

To be successful you will need:

  1. a PhD in computer science or a related discipline, or equivalent industry experience
  2. experience and demonstrable expert knowledge in machine learning and deep learning, ideally including one or more of the following areas: classification/detection in images/audio, object tracking in video, representation learning, few-shot learning, transfer learning, domain adaptation, long-tail learning, open-set recognition, zero-shot learning, graphical models
  3. strong programming skills, including expertise in relevant languages (e.g. Python, C++) and libraries (e.g. NumPy, PyTorch, TensorFlow)
  4. track record of publications in top-tier venues for machine learning, artificial intelligence, computer vision, natural language processing and/or robotics (e.g. NeurIPS, ICLR, CVPR, ICCV, ECCV, PAMI, ICML, JMLR, EMNLP, ACL, ICRA, IROS), commensurate with experience and opportunity
  5. a strong work ethic, and the ability to work well independently, and as a member of a broader team, including with industrial partners
  6. fluency in written and spoken English, with an ability to communicate scientific ideas to an expert audience
  7. commitment to the principles of equity, diversity and inclusion.

In addition to the above, to be successful at Level C, you will also need:

  1. post-doctoral research experience (industry and/or academia)
  2. track record of building new research directions and leading quality research programs, evidenced by one or more of: investigator roles in grants, contract research, consultancies, media stories, joint publications with project partners, patents, commercialisations or other non-commercial outcomes.

Enjoy an outstanding career environment.

The University of Adelaide is a uniquely rewarding workplace. The size, breadth and quality of our education and research programs - including significant industry, government and community collaboration - offers you vast scope and opportunity for a long, fulfilling career.

It also enables us to attract high-calibre people in all facets of our operations, ensuring you will be surrounded by talented colleagues, many world-leading. Our work’s cutting-edge nature - not just in your own area, but across virtually the full spectrum of human endeavour - provides a constant source of inspiration.

Our culture is one that welcomes all and embraces diversity consistent with our Staff Values and Behaviour Framework and our values of integrity, respect, collegiality, excellence and discovery. We firmly believe that our people are our most valuable asset, so we work to grow and diversify the skills, knowledge and capability of all our staff.

We embrace flexibility as a key principle to allow our people to manage the changing demands of work, personal and family life. Flexible working arrangements are on offer for all roles at the University.

In addition, we offer a wide range of attractive staff benefits. These include: salary packaging; flexible work arrangements; high-quality professional development programs and activities; and an on-campus health clinic, gym and other fitness facilities.

Learn more at:

Your faculty’s broader role

The Faculty of Sciences, Engineering and Technology is a thriving centre of learning, teaching and research in a vast range of engineering disciplines, computer science - including machine learning, high-level mathematics and architecture, planning and landscape architecture. Many of its academic staff are world leaders in their fields and graduates are highly regarded by employers.

Learn more at:

If you have the talent, we’ll give you the opportunity. Together, let’s make history.

Click on the ‘Apply Now’ button to be taken through to the online application form. Please ensure you submit a cover letter, a full CV (including a publication list and statement of research expertise and interests) and upload a document that includes your responses to all of the selection criteria for the position as contained in the position description or selection criteria document.

Applications close 11:55pm, 19 March 2023.

For further information

For a confidential discussion regarding this position, contact:

Dr Angela Noack
Program Manager, Centre for Augmented Reasoning
P: +61 (08) 8313 8069

You’ll find a full position description below: (If no links appear, try viewing on another web browser or device)

The University of Adelaide is an Equal Employment Opportunity employer. Women and Aboriginal and Torres Strait Islander people who meet the requirements of this position are strongly encouraged to apply.

Similar jobs

Similar jobs