About the role
Machine Learning Pipeline Development & Deployment
Design and deploy scalable ML/DL pipelines for real-time fraud and bot detection in high-volume competitive gaming networks.
Optimize deep learning models for low-latency inference and real-time decision-making.
Automate model training, tuning, and deployment using MLOps best practices.
Implement distributed computing techniques to process large-scale poker data efficiently.
Automation & Bot Detection
Develop and deploy real-time bot detection models, leveraging behavioral biometrics, timing patterns, and clickstream analysis.
Implement graph-based analytics to uncover multi-accounting automation, bot rings, and coordinated fraud.
Optimize AI-driven countermeasures to detect hybrid human-bot play and adversarial AI threats.
Game Theory & Exploitative Modeling
Support the integration of game-theoretic AI models into real-time detection pipelines.
Develop exploitative modeling features to detect unnatural betting patterns.
Implement multi-agent simulations to test and validate anti-cheat AI strategies.
MLOps & Engineering Best Practices
Design and implement robust CI/CD pipelines for ML models in anti-cheat applications.
Ensure high availability and fault tolerance for fraud detection systems.
Optimize inference models for low-latency execution in production environments.
Work with cloud platforms (AWS, GCP, or Azure) to deploy and scale AI security models.
Monitor and log model performance, ensuring continuous improvement and retraining.
Cross-Functional Collaboration
Work closely with data scientists, software engineers, and poker security experts to align ML solutions with business needs.
Collaborate with game developers to integrate anti-cheat AI into poker platforms.
Partner with poker analysts to fine-tune model accuracy and identify new threats.
