Machine Learning Engineer (Risk & Fraud)

Eneba is a gaming marketplace serving 20m+ active users, seeking a Machine Learning Engineer to join their Data team and evolve fraud detection capabilities. You will build and own real-time fraud/risk models, transitioning from legacy manual approaches to an end-to-end ML lifecycle with robust training, deployment, monitoring, and continuous improvement.

• Build and iterate on real-time fraud/risk models using gradient boosting and anomaly detection to score transactions during checkout and support Risk decisioning
• Own the full ML lifecycle for fraud detection models: data exploration, feature engineering, training, evaluation, deployment, monitoring, and continuous improvement
• Design robust evaluation strategies for rare-event, highly imbalanced data, handling delayed/partial ground truth and defining metrics aligned with business constraints
• Partner with Risk, backend, and Data/Platform teams to productionize models behind an API, integrate with the risk engine, and improve model-driven decision flows
• Drive experimentation and feedback-loop initiatives to improve labels and model quality while maintaining reliability, observability, and documentation

• 3+ years of experience as a Machine Learning Engineer or similar applied ML role, ideally with risk/fraud, anomaly detection, credit/default modeling, or rare-event classification
• Strong Python skills and hands-on experience building supervised ML models such as Gradient Boosting/LightGBM, including feature engineering and model evaluation
• Proven ability to design robust experimentation and evaluation under real-world constraints including imbalanced data, delayed labels, and noisy ground truth
• Experience taking models to production and supporting full model lifecycle in collaboration with engineering teams
• Solid knowledge of ML metrics and decisioning: precision/recall, thresholding, calibration, offline vs online performance and translation to business outcomes
• Familiarity with modern MLOps tooling and practices such as MLflow and feature stores like Databricks Feature Store
• Nice to have: experience with real-time/streaming feature pipelines or infrastructure such as Kafka, Flink, Feast and building low-latency model services/APIs

• Flexible work location: office, remote, or opportunity to work and travel
• Employee Stock Options program
• Performance-based bonuses and referral bonuses
• Additional paid leave and personal learning budget
• Paid volunteering opportunities
• Personal and professional growth supported by feedback and promotion processes
• International team with English as business language