Back
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Tier-1 employer and metro location but specialized graph ML reduces applicant density.
Role requires niche graph ML and fraud detection expertise, limiting cross-industry transferability.
Explicit 6+ years and many mandatory graph, Databricks, Spark, and GNN skills make filtering strict.
Develop and maintain a unified, scalable fraud detection graph integrating multiple data sources using Databricks and Spark.
Implement and optimize Graph Data Science algorithms and Graph Neural Networks to identify abusive patterns and generate fraud risk signals.
Own full lifecycle including schema design, large-scale graph ingestion pipelines, production system reliability, operational health, and collaboration with data science and product teams.
Bachelor's or higher degree in Computer Science, Machine Learning, Data Science, or related field.
6+ years professional experience building and deploying data or ML solutions at scale.
Strong Python programming skills and practical experience with Databricks and Spark for data pipeline development.
Hands-on experience with graph platforms (e.g., Neo4j, Amazon Neptune, TigerGraph) and Graph Data Science algorithms like PageRank, Louvain, Label Propagation, Node2Vec.
Experienced in end-to-end graph ML system development including production deployment, monitoring, and optimization.
Skilled in applying advanced graph ML techniques such as Graph Neural Networks with strong understanding of data and ML lifecycle integration.
Background or interest in fraud detection, anomaly detection, and large-scale graph operational challenges including incremental graph refresh and supernode management.