PostDoc Researcher - Graph Representation Learning and Explainable AI
Posted 9 months ago
Accenture Labs Dublin is looking for a Post-Doctoral researcher in the domain of Graph Representation Learning and Explainable AI.
You will be in charge of designing interpretable machine learning models to infer knowledge from a graph of clinical, genomic, and behavioural data. Explanations will use a wide range of techniques, such as rules derived from the deep learning models, gradient-based attribution methods, or graph-based explanations based on network analysis.
The length of the PostDoc is 3 years. You will join a multi-partner project whose goal is identifying factors that can cause development of new medical conditions, and worsen the quality of life of cancer survivors. The project will analyse patient’s clinical, genomic, behavioural data and existing open data in order to determine a follow-up adapted to the individual needs.
Our lab focuses on artificial intelligence, with a strong emphasis on explainable AI, machine learning on knowledge graphs (graph representation learning), and computational creativity. It is co-located with over 100 designers, developers and domain experts at The Dock, Accenture’s newly-created global centre for innovation.
We offer a blend of industrial-related applicative problems and academic-oriented activities, including an open publication policy.
- PhD in computer science, statistics, mathematics or related field.
- Proven communication skills (talks, presentations, academic publications)
- Strong foundation in mathematics, statistics and probability
- Strong knowledge of Machine Learning foundations
- Knowledge of mainstream Deep Learning architectures
- Ability to work creatively and analytically in a problem-solving environment
- Strong Python programming skills
- Hands-on experience with machine learning frameworks e.g. Scikit-learn, TensorFlow, PyTorch, and scientific Python (e.g. numpy)
- Eagerness to contribute in a team-oriented environment
- Publications in flagship conferences such as NeurIPS, IJCAI, ICLR, AAAI, ICML, KDD, The Web Conf, ISWC
- Experience with graph-based knowledge representation (i.e. knowledge graphs)
- Familiarity with graph representation learning (e.g. knowledge graph embeddings, graph neural networks)
- Experience with explainable AI or interpretable machine learning techniques
- Working knowledge of Linux OS and shell scripting
How to Apply