This is a remote position.
Responsibilities:
â Optimize ML model serving for low-latency inference (target: sub-200ms P95) on EKS
â Advise on and implement AWS-native ML infrastructure (SageMaker endpoints, model registry, A/B testing, monitoring)
â Support ML-optimized rule weight calibration — training logistic regression / LightGBM on rule-fi re indicators to learn optimal rule weights from labeled data
â Assist with model retraining pipeline automation and drift detection
â Contribute to model explainability documentation (SHAP-based attribution) for regulatory compliance
â Participate in model governance: version control, audit trails, threshold confi guration per participating institution
â Support load testing and performance benchmarking of the ML scoring pipeline
â Provide input for the technical proposal and architecture documentation
Requirements
Requirements:
â AWS Machine Learning Specialty Certification (or AWS Certifi ed Machine Learning Engineer – Associate) — current and valid
â 3+ years of hands-on experience deploying ML models in production on AWS
â Strong Python skills (scikit-learn, LightGBM/XGBoost, pandas)
â Experience with containerized ML serving (Docker, Kubernetes/EKS)
â Familiarity with model monitoring, drift detection, and retraining pipelines
Preferred Qualifications
â Experience in fraud detection, AML, or fi nancial risk systems
â Familiarity with graph-based ML (GNN, NetworkX) for network analysis
â Experience with Apache Kafka or Apache Flink for streaming ML
â Knowledge of SHAP or other model explainability frameworks
â Experience with SageMaker (endpoints, model registry, pipelines)
Benefits
â Fully Remote
â Flexible working hours (part-time, ~15–20 hours/week)
â Potential to extend engagement based on project phase progression
