Role Overview
Socure is hiring a Data Scientist II to join the Big Data R&D team in a hybrid capacity located in San Francisco, CA. This position suits professionals with a strong background in data science who want to build the core identity trust infrastructure for the digital economy.
Key Responsibilities
Design and implement machine learning, statistical, data mining, and graph-based algorithms to process very large datasets for identity verification and anomaly detection.
Analyze massive datasets to help develop and improve entity-resolution and identity-matching algorithms supporting Deceased Monitoring and compliance products.
Build, maintain, and optimize data processing pipelines, including ETL, normalization, and feature generation using Spark, PySpark, and AWS platforms.
Assist senior data scientists with feature engineering, exploratory data analysis, error analysis, and setting up A/B tests for new signals and models.
Assess new internal and third-party data sources by profiling data quality, running offline experiments, and assessing impact on model performance and coverage.
Write and maintain Python, Scala, or SQL code for data extraction, transformation, and validation while participating in testing and code reviews.
Deliver analytical support to compliance and regulatory product teams through ad hoc investigations, data deep dives, and simple dashboards.
Communicate key insights, data trade-offs, and structured findings clearly to cross-functional partners across Product, Engineering, and Client Analysis.
Demonstrate operational ownership of well-scoped tasks, solving loosely defined problems and iterating quickly in a fast-paced environment.
Requirements
Master’s degree with at least 2 years of professional experience, a Ph.D. with 1+ years of experience in data science or analytics, or equivalent practical experience.
Proficiency in at least one general-purpose programming language commonly used in data science, such as Python or Scala.
Strong expertise in writing and optimizing SQL queries for large datasets within data lake or data warehouse environments.
Practical, hands-on experience using Spark or PySpark alongside common machine learning libraries.
Familiarity with UNIX operating environments and cloud computing tools within the AWS ecosystem like S3 and EMR.
Working knowledge of supervised and unsupervised machine learning methods and foundational statistics, including clustering, evaluation metrics, and similarity measures.
Ability to break down ambiguous problems, ask clarifying questions, and deliver results independently.
Nice to Have
Experience with deep learning frameworks like TensorFlow or PyTorch.
Familiarity with Databricks.
Exposure to graph databases or graph techniques such as Neo4j, AWS Neptune, or GraphFrames.
Bonus familiarity with Elasticsearch, DynamoDB, or workflow automation tools like Airflow.
Skills and Tools
Python
Scala
SQL
Spark / PySpark
AWS (EMR, S3)
Machine Learning libraries (scikit-learn, XGBoost, TensorFlow, PyTorch)
UNIX environments
Graph techniques and databases
Salary and Benefits
Annual Salary: $140,000 to $170,000 (USD)
Employment Type: Full-Time
About the Company
Socure creates identity trust infrastructure for the digital economy, verifying identities in real time and preventing fraud. The organization addresses complex problems that impact businesses, governments, and millions of individuals. Socure is an equal opportunity employer committed to celebrating diversity and offers accommodations throughout the hiring process upon request.
How to Apply
Interested candidates should visit the official Socure careers page to submit an application.
