Doktorand Graph Machine Learning & Financial Crime Analytics (w|m|d) | findic
zeb consulting · BE, DE
5 days agoImpress employers and recruiters.
Choose from hundreds of resume examples.
Impress employers and recruiters.
Choose from hundreds of resume examples.
Tailor your resume to this Doktorand Graph Machine Learning & Financial Crime Analytics (w|m|d) | findic role.
Rezi rewrites your resume against zeb consulting's job description. Free.
Tailor your resume to this Doktorand Graph Machine Learning & Financial Crime Analytics (w|m|d) | findic role.
Rezi rewrites your resume against zeb consulting's job description. Free.
Don't guess if your resume is good enough.
See how it scores against the Doktorand Graph Machine Learning & Financial Crime Analytics (w|m|d) | findic posting at zeb consulting — free, in seconds.
Don't guess if your resume is good enough.
See how it scores against the Doktorand Graph Machine Learning & Financial Crime Analytics (w|m|d) | findic posting at zeb consulting — free, in seconds.
Responsibilities
- Develop machine learning methods for detecting suspicious transaction patterns and complex anomalies in transaction and relationship networks.
- Investigate modern approaches like Graph Neural Networks, self-supervised learning, and contrastive pre-training, especially for scenarios with limited labeled data.
- Develop methods for reliable graph construction and entity resolution, analyzing the impact of incomplete data and faulty relationships on model quality.
- Systematically evaluate new methods for detection performance, robustness, and explainability, and translate suitable approaches into innovative AI solutions for banks and insurance companies.
- Stay current with research in Graph Intelligence and contribute scientific findings to the advancement of data and AI solutions.
Requirements
- Possess a very good Master's degree in Computer Science, Mathematics, Statistics, Physics, or a related quantitative field.
- Currently pursuing or about to commence a PhD.
- Have sound knowledge of Python and PyTorch.
- Experience with clean, reproducible code, Git, and systematic model evaluation.
- Practical experience with PyTorch Geometric or DGL.
- Trained at least one GNN model (e.g., GCN, GAT, GraphSAGE), ideally on realistic data.
- Conceptually and practically understand self-supervised learning, including approaches like reconstruction-based methods, contrastive learning objectives, or masked graph models.
- Familiar with central challenges of graph construction, including entity resolution, record linkage, kNN-based graph construction, and the impact of faulty, missing, or temporally inconsistent edges.
- Very good German language skills (minimum C1 level, fluent negotiation skills).
- Good English language skills (minimum B2 level, fluent).
Skills
- Python
- PyTorch
- PyTorch Geometric
- DGL
- GCN
- GAT
- GraphSAGE
- Self-supervised learning
- Graph Neural Networks
- Entity Resolution
- Git
- Model Evaluation
Location
- Hybrid
Work Type
- Full-time
- Part-time
Experience Level
- PhD student
Education Level
- Master's degree
- PhD