Description

You will design graph data models for financial entities and relationships, building ML pipelines for risk scoring and anomaly detection.

This role is on-site.

Responsibilities

• Translate business questions into graph queries, covering traversals, communities, and temporal patterns.
• Build data pipelines for ingestion, cleaning, labeling, and feature engineering with entity resolution.
• Develop and validate statistical and ML models for risk scoring, anomaly detection, and forecasting.
• Create event-driven analytics with strong time semantics, focusing on event ordering and causality.
• Partner with engineering to productionize models for batch and near-real-time scoring and monitoring.

Required Skills

• 5+ years of experience in data science or a related field.
• Strong foundation in statistics and machine learning, including evaluation and leakage prevention.
• Hands-on experience with Graph DBs (Neo4j) and concepts like node/edge types and temporal modeling.
• Proficiency in Cypher (Neo4j) and/or Gremlin/SPARQL.
• Expertise in Python for data science, including pandas, numpy, and scikit-learn.
• Solid understanding of SQL, ETL, data quality checks, and reproducibility.
• Experience with AWS or GCP cloud data stacks.

Preferred Skills

• Ability to explain complex technical results to non-technical stakeholders.
• Familiarity with data versioning and ETL processes.

Key Skills

Education

Any Gradute