ML + Correlation Engineer

Duration: 6+ Months

Location: 100% Remote

Lead the design, implementation, and ownership of the intelligence layer supporting automated incident classification and correlation. Develop a scalable multi-tier machine learning architecture that combines rules-based logic, gradient boosting, and large language model (LLM) agents while delivering explainable, compliant, and continuously improving model performance.

Requirements:

• XGBoost model development for production machine learning classification.
• Feature engineering for temporal, topological, or semantic data.
• Model risk management aligned with SR 11-7 guidance.

Key Responsibilities:

• Design and own a three-tier classification engine using rules, XGBoost, and LLM agents.
• Build feature engineering pipelines for temporal, topological, and semantic scoring.
• Train, validate, and optimize XGBoost models using historical ServiceNow incident data from the banking environment.
• Implement SHAP explainability for every model classification decision.
• Build and maintain automated monthly model retraining pipelines using AWS Lambda and MLflow.
• Implement model drift detection using Evidently and maintain model governance documentation for regulatory compliance.