Data Scientist II: Big Data & Identity Graph Analytics

JobCubby; San Francisco, Northern (CA, KY); Hybrid; USD 150,000 - 210,000; Full time

Job summary

Socure is seeking a data science/analytics professional to help build graph-based identity graphs and large-scale ML features. You will work with senior scientists to develop algorithms for identity verification and anomaly detection, and to evaluate new data sources that feed our products.

You’ll design data pipelines with Spark/PySpark on AWS, assist with feature engineering, and contribute to model validation and experiments while communicating insights to Product and Engineering teams.

Qualifications

• Master’s degree with 2+ years of data science/analytics experience or PhD with 1+ year.
• Proficiency in Python or Scala for data science tasks.
• Strong SQL skills for large datasets; comfortable in data lake/warehouse.
• Experience with Spark or PySpark and common ML libs.
• UNIX environments and AWS data services familiarity; Databricks a plus.
• Working knowledge of graph techniques or graph databases is a strong plus.

Responsibilities

• Contribute to design and implementation of ML, data mining, and graph‑based algorithms on very large datasets.
• Analyze data to refine entity‑resolution and identity‑matching for compliance solutions.
• Build and maintain data pipelines (ETL, feature generation, normalization) using Spark/PySpark and AWS.
• Support senior data scientists with feature engineering, data exploration, and A/B tests.
• Evaluate new data sources and summarize impact on coverage and model performance.
• Maintain SQL and Python/R code for data extraction, transformation, and validation.
• Provide analytical support to compliance teams, including dashboards and data deep dives.
• Communicate findings clearly to cross‑functional partners and stakeholders.
• Work in a fast‑paced environment with ownership of scoped tasks and delivery.

Skills

Python

Scala

SQL

Spark

ML Libraries

UNIX/AWS

Databricks

Graph Databases

Elasticsearch

Airflow

Education

Master's degree

PhD

Tools

GraphFrames

Neo4j

AWS Neptune

Job description

Socure is seeking a data science/analytics professional to help build graph-based identity graphs and large-scale ML features. You will work with senior scientists to develop algorithms for identity verification and anomaly detection, and to evaluate new data sources that feed our products.

You’ll design data pipelines with Spark/PySpark on AWS, assist with feature engineering, and contribute to model validation and experiments while communicating insights to Product and Engineering teams.