Role: ML + Correlation Engineer (Full-Stack AI Engineer)
Location's:  Jersey City, NJ | Columbus OH | Dallas TX
Contract role.
 

In-person interview required.
 

Key Responsibilities:

• Build and own the intelligence layer for correlation and classification

• Design and implement multi-tier classification engine (rules, XGBoost, LLM agents)

• Develop feature engineering pipelines (temporal, topological, semantic scoring)

• Train, validate, and optimize ML models using historical incident data

• Implement SHAP-based explainability for model decisions

• Build and manage model retraining pipelines (Lambda + MLflow)

• Implement model monitoring and drift detection (Evidently)

• Develop real-time streaming pipelines (Kafka/Redis)

• Build backend services using Python (FastAPI, async programming)

• Integrate with enterprise systems (ServiceNow, Splunk, Dynatrace)

• Implement vector databases and LLM-based agents

• Deploy and maintain production-grade AI systems on enterprise infrastructure

• Maintain model risk documentation (SR 11-7 compliance)

Required Skills:

• Strong Python engineering (async programming, FastAPI)

• ML frameworks: XGBoost, scikit-learn

• ML lifecycle tools: MLflow

• Feature engineering & model explainability (SHAP)

• Streaming technologies: Kafka / Redis

• Strong SQL skills

• Experience with API integrations (ServiceNow, Splunk, Dynatrace)

• Experience with LLMs, vector databases, and agent-based architectures

• Production deployment experience in enterprise environments

Nice to Have:

• Financial services / banking ML experience

• Experience with model governance and compliance (SR 11-7)

Note:

• This is a full-stack AI engineering role, not a pure data science position

• Candidate must be able to build, integrate, and deploy end-to-end production systems