> Markdown version of [/jobs/ext/4760663-data-scientist-career](https://www.wearedevelopers.com/jobs/ext/4760663-data-scientist-career). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Data Scientist - Career - **Company:** Equifax - **Location:** Johns Creek, GA, United States - **Experience:** Expert - **Contract:** Permanent contract - **Skills:** Clean Code Principles, Amazon Web Services, Data Analysis, Artificial Neural Networks, Big Data, Cloud Computing, Software Documentation, Software Quality, Code Review, Computer Programming, Databases, Continuous Integration, Information Engineering, Data Mining, Fraud Prevention and Detection, Graph Database, Python (Programming Language), Link Analysis, Machine Learning, Neo4j, NumPy, Performance Tuning, Tensorflow, Azure Data Lake, Software Engineering, SQL Databases, Google Cloud, Feature Engineering, Sql Optimization, Graph Neural Networks, Boosted Trees, Pytorch, Delivery Pipeline, Deep Learning, Model Validation, Git, Pandas, Scikit Learn, Information Technology, Xgboost, Machine Learning Operations, Entity Resolution, GPT, Software Version Control, Recurrent Neural Networks - **Published:** November 17, 2026 - **Apply:** https://equifax.wd5.myworkdayjobs.com/External/job/USA---Georgia---Alpharetta---30005/Data-Scientist---Career_J00180107 ## About the Role * Education: Master's degree (or equivalent practical experience) in a highly quantitative STEM field: Statistics, Computer Science, Physics, Mathematics, Engineering, Data Science, or related discipline. * Identity & Graph Experience: Hands-on experience with graph neural networks (GNNs) or graph databases (e.g., Neo4j, NetworkX) for entity resolution and graph-based feature engineering. * Experience: 5 to 7 years of hands-on data science experience, with direct focus on developing predictive models for fraud risk, identity resolution, or risk management. Technical Skills * Machine Learning & Modeling: Deep expertise in tree-based ensembles (XGBoost, LightGBM) and modern deep learning models (Transformers, Neural Networks, Sequence Models). * Programming & Database: Advanced Python (Pandas, NumPy, Scikit-Learn, PyTorch/TensorFlow) and expert-level SQL query development for complex data extraction and feature engineering. * Software Development & MLOps: Proficiency with version control software, CI/CD practices, modular code design, and statistical repositories. * Model Evaluation: Strong grounding in stress-testing models, cross-validation on highly imbalanced target distributions, model explainability, and performance tuning. What could set you apart * Cloud Infrastructure: Experience working in cloud environment deployment workflows (AWS, GCP, Azure Data Lake / SageMaker) with Cloud Certification preferred. * Regulatory Knowledge: Familiarity with MRM documentation standards (e.g., SR 11-7 guidelines) and model governance protocols., * Cross-Functional Collaboration: Communicates complex ML concepts clearly to non-technical stakeholders while aligning technically with MRM. ## Description As a Data Scientist (P3) on the Fraud Modeling Team, you will lead the design, development, and deployment of high-impact machine learning and advanced statistical models to combat First-Party Fraud, Third-Party Fraud, Synthetic Identity Fraud, and support Identity Graph Analytics. Operating independently within a collaborative matrixed environment, you will bridge technical model execution with commercial outcomes. You will collaborate closely with cross-functional partners-including Product, Sales, Core Analytics, and Model Risk Management (MRM)-to build stress-tested, deployable fraud detection engines, ensure regulatory alignment, and communicate technical business impact to leadership. What You'll Do * Fraud Model Development & Optimization: Independently design, train, and optimize predictive models using XGBoost, Gradient Boosted Trees, Transformer-based models, and deep learning architectures tailored for high-dimensional, imbalanced fraud datasets. * Identity Graph & Identity Analytics: Leverage graph structures and identity link analysis to detect synthetic identity networks, fraud rings, and suspicious identity resolution patterns across large datasets. * Domain Focus Areas: Develop actionable fraud detection frameworks targeting First-Party Fraud, Third-Party Fraud, and Synthetic Identity Fraud. * Stakeholder Management & Governance: + Partner with product and sales to translate market requirements into technical model specifications and vice versa. + Collaborate with Model Risk Management (MRM) to pass model validation, conceptual soundness checks, and compliance reviews. * Data Engineering & Querying: Query, manipulate, and structure massive historical dataset assets using advanced SQL and Python to engineer complex behavioural features and fraud signals. * Production & Code Quality: Write clean, modular, and efficient code following version control best practices (Git). Contribute to core internal code repositories and perform code reviews for peer accuracy. * Technical Mentorship & Storytelling: Package complex statistical outputs into visual narratives and executive presentations for mid-level leadership and non-technical stakeholders. Mentor junior data scientists on modeling standards.