Data Scientist (Big Data R&D, Identity Graph & KYC)

Role overview

Join Socure’s Big Data R&D team as a Data Scientist working on graph-based algorithms and data pipelines over massive PII datasets. You’ll help design and implement machine learning, data mining, statistical, and graph-based approaches that improve entity resolution and identity matching for KYC and compliance.

Responsibilities

• Design and implement machine learning, data mining, statistical, and graph-based algorithms for very large datasets.
• Analyze large datasets to develop and refine entity resolution and identity matching algorithms powering KYC and compliance solutions.
• Build and maintain data pipeline components including ETL, feature generation, and normalization.
• Collaborate with senior data scientists and engineers to deliver models and data products.

Requirements

• Hands-on experience with Spark or PySpark and common ML libraries (e.g., scikit-learn, XGBoost, TensorFlow/PyTorch as a plus).
• Strong experience writing and optimizing SQL for large datasets; comfortable working in data lake/warehouse environments.
• Working knowledge of supervised and unsupervised ML plus basic statistics (e.g., similarity measures, clustering, evaluation metrics).
• Proficiency in at least one general-purpose data science language: Python or Scala.
• Ability to break down loosely defined problems, ask clarifying questions, and iterate quickly.
• Master’s degree + 2+ years of experience, or Ph.D. + 1+ years, or equivalent practical experience.

Nice-to-haves

• Exposure to graph techniques or graph databases (e.g., Neo4j, AWS Neptune, GraphFrames).
• Experience with Elasticsearch or DynamoDB.
• Airflow for automating data pipelines.
• Familiarity with UNIX and the AWS ecosystem (e.g., EMR, S3), and Databricks experience.

Location / work setup

• Full remote