Description

Design and optimize alerting thresholds and anomaly detection logic for large-scale monitoring systems to enhance signal quality and reduce noise.

This role is hybrid.

Responsibilities

• Develop and apply machine learning models, including anomaly detection, clustering, and pattern recognition, to identify abnormal behavior across datasets.
• Enable GenAI-powered and agent-based workflows to automate alert analysis, enrichment, and triage recommendations.
• Build and maintain data pipelines and analytical workflows in Databricks and enterprise data platforms to support near real-time alerting.
• Analyze alert data to identify false positives and missed detections, implementing improvements to enhance alert quality and precision.
• Define and track alert performance metrics to continuously improve signal effectiveness while ensuring models are explainable, traceable, and audit-ready.

Required Skills

• 5+ years of experience in data science, analytics, or machine learning.
• Proficiency in Python and SQL for data analysis and model development.
• Hands-on experience with Databricks or equivalent large-scale data platforms.
• Solid understanding of anomaly detection techniques, threshold calibration, and signal optimization.
• Experience with ML model behavior evaluation and performance metrics.
• Understanding of AI/GenAI concepts and agent-based architectures.
• Experience with visualization tools such as Power BI or similar dashboards.

Preferred Skills

• Exposure to Splunk, Datadog, TMX, BioCatch, or similar alerting platforms.
• Experience in fraud, cybersecurity, or operational risk analytics.

Key Skills

Education

Any Graduate