(USA) Senior, Data Scientist

Wal-Mart•Bentonville, AR

55d

About The Position

Walmart's Decision Management Team supports the growth of the e-Commerce Marketplace program through the practical application of data science and advanced analysis to optimize risk decision strategies. This includes data analysis, advanced statistics, case investigation and application of advanced modeling techniques to manage risk on the ecommerce platform. We work alongside business, product, and engineering teams to deliver solutions to manage Marketplace risk. What You'll Do… As a Senior Data Scientist, you will drive both analytical insight and technical model development to detect and mitigate fraud and performance risks. You'll work on high-impact problems that require a mix of rigorous analysis, experimentation, and machine learning. This role is ideal for someone who is comfortable moving between deep analytics and building scalable models in production.

Requirements

Strong understanding of machine learning, data exploration, statistical modeling, and their application to risk and fraud detection in digital marketplaces.
Demonstrated experience developing and deploying models to identify anomalous behavior, detect fraud, or assess risk in real-time systems.
Proficiency in Python, SQL, and data science libraries/frameworks such as scikit-learn, XGBoost, TensorFlow, or PyTorch.
Familiarity with Agentic AI systems or AI agents-understanding of how autonomous models can be leveraged in dynamic decision environments.
Experience conducting experimentation and model validation using rigorous statistical methods (e.g., A/B testing, ROC/AUC, precision/recall).
A strong problem-solving mindset and ability to translate ambiguous business problems into clear analytical frameworks.
Excellent written and verbal communication skills, with the ability to explain technical concepts to diverse audiences.
Experience with data visualization tools (e.g., Tableau, Power BI, matplotlib, seaborn) to craft compelling insights.
Option 1: Bachelor's degree in Statistics, Computer Science, Data Science, Mathematics, or related field, with 5+ years of hands-on experience in data science, machine learning, or risk management.
Option 2: Master's degree in a related field (e.g., Data Science, Machine Learning, Statistics, Applied Mathematics) with at least 3+ years of applied experience working on data-driven risk management or fraud prevention.
Option 3: 6-8 years of direct experience in data science, machine learning, or applied risk management within an e-commerce or marketplace setting.

Nice To Haves

Expertise in using advanced machine learning techniques such as deep learning, reinforcement learning, or anomaly detection for fraud detection or risk mitigation.
Understanding of LLMs, agentic workflows, or prompt engineering concepts in the context of AI-enhanced decision systems.
Experience with big data technologies like Apache Spark, Hadoop, and cloud-based data solutions (e.g., AWS, Google Cloud) to build scalable risk management platforms.
Proficiency in data manipulation and analysis tools such as Pandas, NumPy, and SQL for data wrangling, feature engineering, and analysis.
Strong background in model evaluation techniques including ROC/AUC, confusion matrices, precision/recall, and F1 scores, as well as experience with A/B testing and model validation.

Responsibilities

Develop Risk Mitigation Models using machine learning, anomaly detection, and statistical techniques to identify and respond to emerging risk trends on the Marketplace platform.
Analyze Risk Patterns by exploring large datasets to uncover emerging fraud tactics, behavioral anomalies, and areas of business exposure.
Develop Predictive Models using supervised and unsupervised learning techniques to power risk detection systems at scale.
Lead Deep-Dive Analytics to inform risk policy, product decisions, or operational strategies-identifying key drivers, trends, and optimization opportunities.
Integrate Agentic AI Frameworks to support semi-autonomous risk detection systems that can adapt and respond to evolving fraud patterns in real-time.
Explore Generative AI (GenAI) Applications for synthetic data generation, anomaly simulation, or scenario modeling to improve risk model robustness.
Collaborate Cross-Functionally with product, engineering, and operations teams to ensure seamless integration of data science solutions into business workflows.
Monitor Model Performance and proactively identify areas for improvement using quantitative metrics, feedback loops, and model diagnostics.
Bridge Analytics and Science by combining robust data analysis with model development to create solutions that are both explainable and effective.
Translate Insights into Action by communicating complex analytical findings clearly to both technical and non-technical stakeholders.
Design and Execute Experiments (e.g., A/B tests, statistical validations) to evaluate model impact and improve decision strategies.