Director of Data Science, Identity and Fraud (Finance)

Equifax is seeking a Director of Data Science to lead our Fraud and Identity Team in our Boise, Idaho office.

This is a hands on player/coach role and a great opportunity to join a tight knit growing team. This role is required to be in our Boise office 3 days/week on Tuesdays, Wednesdays and Thursdays.

What you will do

• Utilize subject matter expertise of data structures, analytics, algorithms/models, and strong computer science fundamentals to lead data preparation, analytics, and development of deployable solutions across multiple projects
• Collect, analyze and interpret large data assets to define and build multiple innovative solution components leveraging business and technical expertise. Lead the analytical strategy on critical technical capabilities
• Evaluate new data sources, provide recommendations on the value of data sources, and design code to improve the productivity of Equifax, enhance and update code where needed. Ensure quality of the code is intact.
• Manages teams that lead multiple programs of solutions that generate significant Equifax revenue. Facilitates stakeholder collaboration to support the development of predictive models, risk assessments, fraud detection, recommendation engines, etc. influencing decisions on the solution and enabling teams to execute, escalating and removing obstacles as appropriate.
• Conduct resource assignment and weigh multiple priorities to drive the right business decisions
• Partner across multiple functional units to execute goals
• Package, summarize, visualize and perform storytelling on analytical findings and results for management and senior business users
• Communicate results to senior management and external stakeholders, able to communicate the strategic impact of the work
• Architect multiple innovative solution components leveraging business and technical expertise
• Perform as lead technical data scientist for multiple technical and business domains.
• Evaluate the technical work of experienced data scientists guiding them on deliverable quality and accuracy

What experience you need

• BS degree in a STEM major or equivalent discipline; Master's Degree strongly preferred
• 7+ years of related experience with experience demonstrating leadership capabilities and/or functioning as a team lead/supervisor
• Advanced Machine Learning & Statistical Modeling: Deep theoretical and practical expertise in a wide range of machine learning algorithms (e.g., supervised, unsupervised, reinforcement learning), statistical modeling techniques, and predictive analytics.
• Graph Databases & Network Analysis: Experience with graph databases (e.g., Neo4j, Neptune) and apply network analysis techniques to identify complex relationships, and anomalies that traditional methods may miss.
• Proficiency in Deep Learning Frameworks: Command of at least one major deep learning framework, such as TensorFlow or PyTorch, as well as, an understanding of transfer learning, text embedding, RAG, LLM fine tuning and Agentic AI.
• Programming & Scripting: Expert-level proficiency in programming languages commonly used in data science, such as Python (with libraries like scikit-learn, TensorFlow, PyTorch, Pandas, NumPy), R, or SAS.
• Data Manipulation & Feature Engineering: Strong capabilities in data extraction, transformation, and loading (ETL), as well as advanced feature engineering to prepare diverse datasets for robust model development. Pipeline development and optimization.
• Model Validation & Explainability: Experience with rigorous model validation techniques, performance evaluation metrics (e.g., precision, recall, F1-score, KS, AUC-ROC for imbalanced classes), and model interpretability/explainability (XAI) frameworks.
• Cloud certification strongly preferred
• Additional role-based certifications may be required depending upon region/BU requirements

What could set you apart

• Experimentation & A/B Testing: Familiarity with designing and executing A/B tests and other experimental methodologies to evaluate the effectiveness of fraud strategies and models.
• Big Data Technologies & Distributed Computing: Hands-on experience with big data platforms (e.g., Spark, Kafka) and cloud-based data warehouses(e.g., BigQuery, Snowflake, Redshift), along with proficiency in distributed computing for large-scale data processing and model training.