Expression of interest: PhD Position for Domestic Students
Deep Learning for Functional Annotation of Genome
About the Opportunity
The National Centre for Indigenous Genomics (NCIG) is advancing genomic medicine for Indigenous Australians through the creation of culturally appropriate genomic data resources, including Australia's first Indigenous pangenome. We are seeking outstanding PhD candidates to develop novel deep learning algorithms and GPU-based genomic data solutions. The overarching goal is to enable functional interpretation of genomic variations (particularly in pharmacogenes) for precision healthcare applications.
This position is based at The Australian National University (ANU) in Canberra, consistently ranked among the world's most livable cities. ANU provides a world-class research environment with state-of-the-art facilities, access to Gadi (Australia's most powerful research supercomputer), and a vibrant academic community at the forefront of computational genomics and Health AI.
Research Focus & Impact
As a PhD candidate, you will contribute to pioneering research with the potential to transform healthcare outcomes for underrepresented communities. Your work will include:
* Designing and implementing data solutions tailored for genomic data
* Developing machine learning tools that incorporate state-of-the-art methods, including transformers, graph neural networks, physics-informed models, and generative approaches
* Integrating and analyzing multimodal sequencing and omics datasets
* Collaborating with wet-lab scientists and an international network of researchers
* Embedding ethical AI, and culturally responsive approaches into your research
Key Qualifications
* Master's degree or Bachelor's with Honours in Computer Science, Artificial Intelligence, Bioinformatics, Physics, Mathematics, Engineering, Bioengineering, or a related quantitative field
* Demonstrated proficiency in deep learning frameworks (TensorFlow, PyTorch, or JAX)
Desirable Skills and Experience
* Experience working with genome-scale datasets
* Experience with sensitive data and HPCs
* Familiarity with containerization tools (e.g., Docker, Singularity)
* Knowledge of data-unified programming models (e.g., Arrow)
* Familiarity with graph neural network
* Proficiency in CUDA C/C++
* Experience with version control systems
* Familiarity with ML production pipelines and MLOps
To express your interest, please submit:
* Detailed CV including academic transcripts
* Cover letter outlining your research interests and career goals
* Portfolio of relevant projects or publications (if available)
#J-18808-Ljbffr