Description :

Primary Tech Skills :

Python (Required) :

- Advanced experience building analytical tooling, scoring logic, or offline detection workflows.

- Automation, preprocessing, and feature engineering for fraud datasets.

AWS (Required) :

- Hands-on experience with Lambda, S3, Glue, Step Functions, EventBridge.

- Ability to build scalable, secure data pipelines for fraud detection and reporting.

SQL (Required) :

- Strong ability to query complex fraud datasets, join across multisource data, and perform anomaly identification and rule performance analytics.

Fraud Expertise (Required) :

- Experience with fraud models, rules, behavioral analytics, or earlylife monitoring.

- Understanding of fraud patterns across account takeover, application fraud, payment fraud, synthetic identity, and digital channel risk.

- Ability to translate fraud behaviors into analytical detection methods or rule logic.

- Senior Data Analyst, Specialist

Role Overview :

The Senior Data Analyst, Specialist leads advanced analytical and data engineering initiatives that directly support fraud detection, rule strategy, and threat mitigation across ES&F.

This role is highly technical and focuses on building scalable data pipelines, offline fraud detection logic, rule performance analytics, and deep pattern analysis to identify emerging fraud behaviors.

Candidates must have meaningful fraud experience in financial services, banking, or fintech, including working with fraud models, rules, or earlylife strategy performance.

Key Responsibilities :

Fraud Detection, Rule Development & Pattern Analysis :

- Develop offline fraud detection logic, heuristic approaches, and analytical frameworks to identify suspicious activity, fraud patterns, and anomalies.

- Conduct in-depth analysis of transactional, behavioral, device, and metadata signals to support new rule development and enhancement of existing strategies.

- Evaluate rule performance, precision/recall, false positives, and emerging patterns to recommend optimizations and mitigate fraud losses.

- Partner with Fraud Operations, Fraud Strategy, and Risk teams to translate fraud trends into scalable rule concepts or model features.

- Support earlylife monitoring of new strategies, rules, models, and controls to validate effectiveness and identify unintended impacts.

Data Engineering & Analytical Workflows :

- Design and build Python-based applications, data pipelines, and analytical tools that enable fraud detection, model monitoring, and rule analytics.

- Build and maintain AWS-based data engineering workflows (Lambda, S3, Glue, Step Functions, EventBridge) that process fraud and transaction data efficiently and securely.

- Implement production-quality code using best practices in testing, documentation, version control, CI/CD, and secure data handling.

Operational Ownership & Process Leadership :

- Own and maintain critical fraud reporting, detection workflows, and analytical infrastructure.

- Proactively identify opportunities to automate manual fraud analytics processes and improve operational efficiency.

- Ensure high data quality, accuracy, and consistency across fraud detection and rule analytics pipelines.

Additional Responsibilities :

- Support special initiatives, deep dives on emerging threats, and strategic fraud projects.

- Perform additional duties aligned with evolving fraud and business priorities.

Required Qualifications :

- Minimum five years of experience in data analytics, data engineering, or highly technical fraud roles.

Required fraud domain experience :

- Hands-on experience with fraud models, rule development, rule performance monitoring, or earlylife strategy evaluation.

- Fraud experience within financial services, banking, or fintech.

- Proven experience designing and developing Python applications and building AWS data pipelines.

- Strong analytical, investigative, and problem-solving skills, with emphasis on fraud pattern detection.

- Undergraduate degree or equivalent experience.

Preferred Skills :

- Experience with feature engineering for fraud models.

- Exposure to supervised/unsupervised techniques supporting fraud detection (optional but beneficial).

- Experience with metadata, device, network, or behavioral signal analysis.

- Familiarity with enterprise security or identity risk environments