Data Scientist II - Big Data Graph & Identity Monitoring

Socure; Seattle (WA); On-site; USD 140,000 - 170,000; Full time

Job summary

Socure is hiring for a Big Data R&D role focused on graph-based ML and large-scale data pipelines. You will work with senior data scientists to develop identity verification and anomaly-detection algorithms on massive PII datasets.

You will build ETL components with Spark/PySpark and AWS, support feature engineering, and evaluate new data sources to improve model coverage and performance. Strong SQL and Python/Scala skills required.

Qualifications

• Master’s degree in data science or related field with 2+ years of experience, or Ph.D. with 1+ years.
• Proficiency in Python or Scala for data science tasks.
• Strong SQL skills for large datasets; experience with data lakes/warehouses.
• Hands-on experience with Spark or PySpark and common ML libraries (scikit-learn, XGBoost).

Responsibilities

• Design and implement ML, data mining, statistical and graph-based algorithms for large datasets.
• Develop entity-resolution and identity-matching algorithms.
• Build and maintain ETL pipelines and feature generation using Spark/PySpark and AWS.
• Assist with feature engineering, data exploration, and A/B test setup for models and signals.
• Evaluate new data sources and assess impact on coverage and model performance.
• Write and optimize SQL/Python/R code for data extraction, transformation, and validation.
• Provide analytical support to compliance and regulatory teams with dashboards and data dives.
• Communicate findings clearly to Product, Engineering, and Client Analysis teams.

Skills

Python

Scala

SQL

Spark

Pandas

Statistics

Education

Master’s degree in data science

Ph.D.

Equivalent practical experience

Tools

Spark/PySpark

SQL databases

AWS (EMR, S3)

Databricks

Neo4j / Neptune

Airflow

TensorFlow/PyTorch

Job description

Socure is hiring for a Big Data R&D role focused on graph-based ML and large-scale data pipelines. You will work with senior data scientists to develop identity verification and anomaly-detection algorithms on massive PII datasets.

You will build ETL components with Spark/PySpark and AWS, support feature engineering, and evaluate new data sources to improve model coverage and performance. Strong SQL and Python/Scala skills required.