Senior ML Data Scientist - Fraud Detection & Impact

Adobe; San Jose (CA); Hybrid; USD 163,000 - 236,000; Full time

Benefits offered by this job

Hybrid work model

Job summary

Adobe seeks a Senior Machine Learning Data Scientist to build fraud and abuse detection models and measure their effectiveness across the fraud lifecycle. You will work hands-on with Python and SQL on large datasets, developing evaluation frameworks and translating detection performance into business insights for engineering and risk teams.

The role requires 8+ years in applied ML, strong statistical foundations, and the ability to communicate results to executives in a hybrid work setting.

Qualifications

• 8+ years in applied Data Science / ML with production models.
• Strong hands-on Python and SQL skills with large, complex datasets.
• Experience with model monitoring, drift, false-positive/false-negative analysis.
• Strong data visualization and storytelling skills.
• Bachelor’s or equivalent in Statistics, Mathematics, CS, or related field; advanced degree a plus.

Responsibilities

• Build and tune ML models for fraud and abuse detection.
• Develop robust evaluation frameworks, datasets, and metrics.
• Analyze false positives/negatives, model drift, and emerging fraud patterns to improve detection.
• Define ground truth, labeling approaches, and fraud taxonomies.
• Design experiments and evaluate tradeoffs across precision, recall, and business impact.
• Build dashboards and metrics translating detection performance to business impact.
• Pressure-test models and data for leakage, bias, and data quality issues.
• Partner with engineering, product, policy, and risk teams to implement improvements.

Skills

Data Science

Machine Learning

Python

SQL

Model Evaluation

Data Visualization

Experimentation

Statistics

Education

Bachelor’s degree in Statistics, Mathematics, Computer Science, or related field

Tools

Python

SQL

Job description

Adobe seeks a Senior Machine Learning Data Scientist to build fraud and abuse detection models and measure their effectiveness across the fraud lifecycle. You will work hands-on with Python and SQL on large datasets, developing evaluation frameworks and translating detection performance into business insights for engineering and risk teams.

The role requires 8+ years in applied ML, strong statistical foundations, and the ability to communicate results to executives in a hybrid work setting.