Data Scientist II - Big Data R&d, Identity Graph & Kyc

Socure Socure · Vertical AI · United States · Remote · Data Science & AI

This role focuses on building core identity graph and entity-resolution capabilities using graph-based algorithms and data pipelines on large PII datasets. It involves feature engineering, data processing, and supporting modelers for KYC and compliance products. The role requires strong skills in data processing, ML, and distributed systems.

What you'd actually do

  1. Contribute to the design and implementation of machine learning, data mining, statistical, and graph-based algorithms to analyze very large datasets for identity verification and anomaly detection.
  2. Analyze large datasets to help develop and refine entity-resolution and identity-matching algorithms that drive Socure’s KYC and compliance solutions.
  3. Build and maintain components of data-processing pipelines (ETL, feature generation, normalization) using tools such as Spark/PySpark and AWS (e.g., EMR, S3).
  4. Support senior data scientists with feature engineering, data exploration, error analysis, and A/B test setup for new models and signals.
  5. Help evaluate new third‑party and internal data sources: profile data quality, design offline experiments, and summarize impact on coverage and model performance.

Skills

Required

  • Python
  • SQL
  • Spark/PySpark
  • AWS
  • machine learning
  • data mining
  • statistical algorithms
  • graph-based algorithms
  • ETL
  • feature generation
  • data processing pipelines
  • data exploration
  • error analysis
  • A/B testing
  • data quality profiling
  • offline experiments
  • data source evaluation
  • Unix environments
  • supervised/unsupervised ML
  • basic statistics

Nice to have

  • Scala
  • scikit-learn
  • XGBoost
  • TensorFlow
  • PyTorch
  • Databricks
  • graph techniques
  • graph databases
  • Neo4j
  • AWS Neptune
  • GraphFrames
  • Elasticsearch
  • DynamoDB
  • Airflow

What the JD emphasized

  • large datasets
  • identity verification
  • entity-resolution
  • KYC
  • compliance

Other signals

  • identity verification
  • fraud detection
  • entity resolution
  • graph-based algorithms
  • large-scale ML