Equifax is hiring a Data Scientist to join the Entity Resolution/Keying & Linking team within Global Data & Analytics. This hybrid role (Alpharetta, GA) focuses on turning diverse, sometimes messy data into dependable analytical and AI solutions, using cloud-based tools and data/ML techniques to support teams across the globe.
You will help integrate standard and new data sources, develop and test AI methodologies, and build deployable solutions with guidance from more senior teammates. You will also package and communicate results to management, while collaborating with regional and global Equifax teams to improve workflows and align on best practices.
Responsibilities
- Partner with key stakeholders to understand needs, applying knowledge of data structures, analytics, algorithms/models, and core computer science to prepare datasets and develop, test, and enhance tools for Global Data & Analytics teams.
- Analyze and prepare complex and new data sources, assembling data from standard and emerging sources for analytical use.
- Work on moderate complexity tasks across multiple business and analytical domains, including predictive models, risk assessments, fraud detection, and recommendation engines.
- Develop deployable solutions with support from more senior resources.
- Package, summarize, and visualize analytical findings and results for management audiences.
- Evaluate the work of peer and/or junior data scientists to help ensure high-quality solutions.
- Conduct A/B testing to determine which techniques and algorithms perform best.
- Use Google Cloud Platform (GCP) technologies and stay current on cloud advancements to recommend optimization and automation improvements, including agentic workflows.
- Collaborate with regional and global teams to share insights, standardize workflows, and adopt best practices.
Requirements
- BS degree in a STEM major or equivalent discipline (Mathematics, Statistics, or Computer Science preferred).
- 2 to 5 years of experience in a related analytical role, including experience designing and developing predictive models.
- Cloud certification strongly preferred.
- Core tech: strong proficiency in Python and SQL, with practical experience writing utility scripts.
- Cloud infrastructure: understanding of cloud computing concepts, with hands-on experience in GCP (or a similar cloud environment).
- Data modeling: experience transforming unstructured/structured data into optimized models, troubleshooting pipeline bottlenecks, and ensuring data readiness.
- Version control: solid experience with Git.
Technologies
- Python, SQL
- Google Cloud Platform (GCP), Google BigQuery, BigQuery, BigTable
- Dataflow
- PySpark/Scala
- Git
Benefits
- Comprehensive compensation and healthcare packages
- 401k matching
- Paid time off
- Organizational growth potential through an online learning platform with guided career tracks
What could set you apart
- Master's degree or higher in Mathematics, Computer Science, Engineering, Operations Research, Statistics, or a related discipline (strongly preferred)
- Knowledge and experience with Data Engineering
- Exposure to credit/financial data products, or prior project/academic experience with Entity Resolution and identity matching concepts
- Hands-on experience with Google BigQuery, BigTable, Dataflow, or big data processing frameworks like PySpark/Scala
- Experience developing Machine Learning algorithms for production systems
- DevOps basics and exposure to CI/CD integration workflows
- Ability to communicate and present effectively to all levels