The business problem is to increase the scalability and value of Artificial Intelligence and Machine Learning use cases through Semantic data integration and curation strategies. Chase aims to leverage advanced Semantic-based Artificial Intelligence and Machine Learning techniques to develop state-of-the-art prediction, forecasting, and agentic systems.
Requirements
- Programming Languages – Python, Java
- Query Languages – SPARQL, SQL
- Semantic Vocabularies – RDF, R2RML, OWL, RDFS, XSD
- Machine Learning – Feature Engineering, Hyperparameter Optimization, Model Evaluation
- Python Libraries – RDFLib, mOWL, PyKEEN
- Query Optimization and Rewriting – Virtual Tables/Views, OWL QL
- Graph Machine Learning – Knowledge Graph Embeddings, Graph Neural Networks
Responsibilities
- Model domain knowledge related to our Marketing businesses.
- Build ontology and mapping files to integrate multi-platform data ecosystems.
- Curate Machine-Learning ready knowledge graphs by querying petabytes of financial data.
- Embed knowledge graphs into domain-specific vector spaces.
- Concatenate embeddings into wholistic feature spaces.
- Train Graph Neural Network models using embedded feature spaces.
- Evaluate Graph Neural Network models using recommender-based scoring metrics.
Other
- 2 years of work experience leveraging Semantic Data Science or related techniques
