Staff Data Scientist — Fraud ML & Scalable Models

Walmart; Pierre (SD); On-site; USD 27,552 - 41,328; Full time

Benefits offered by this job

Performance incentive awards

401(k) match

Stock purchase plan

Paid maternity and parental leave

Paid time off (PTO)

Fitness plans

Job summary

Walmart (Sam’s Club) in the United States is seeking a Staff Data Scientist to advance fraud detection through machine learning across multiple domains. You will translate business problems to data‑science solutions and develop scalable models for large-scale data mining and graph analytics.

The role collaborates with engineering to deploy model pipelines and respond to system issues with root‑cause analysis, using Python, SQL, Spark, and GCP tools.

Qualifications

• Bachelor’s degree with 4+ analytics years of experience.
• OR Master’s degree with at least 2 years analytics experience.
• OR at least 6 years analytics experience in a related discipline.

Responsibilities

• Use machine learning to improve fraud detection models across multiple areas.
• Partner with cross-functional teams to translate fraud business problems into data‑science solutions.
• Develop scalable ML models and algorithms in large-scale data mining and graph modeling.
• Collaborate with engineering to build and deploy model pipelines at scale.
• Respond quickly to system issues and perform root‑cause analysis.

Skills

Production-scale systems

Python

SQL

PySpark

BigQuery/GCP

Fraud risk solutions

Cross-functional collaboration

Education

Bachelor’s degree in analytics/statistics

Master’s degree in a related field

Six years analytics experience

Tools

scikit-learn

TensorFlow

PyTorch

Spark

Scala

R

BigQuery

Job description

Walmart (Sam’s Club) in the United States is seeking a Staff Data Scientist to advance fraud detection through machine learning across multiple domains. You will translate business problems to data‑science solutions and develop scalable models for large-scale data mining and graph analytics.

The role collaborates with engineering to deploy model pipelines and respond to system issues with root‑cause analysis, using Python, SQL, Spark, and GCP tools.