Principal Data Scientist - Anti-Cheat

About the job

A5 Labs offers best-in-breed AI-driven security solutions that ensure fair play and integrity across all strategy-based games, including online games and beyond.

Our proprietary neural networks and deep reinforcement learning models enable non-invasive, high-accuracy detection systems for competitive play. By combining advanced automation detection, exploitative modeling, and AI-driven game security, we help online gaming operators maintain trust, fairness, and integrity at scale.

As part of our team, you will be at the forefront of AI security research and development, building cutting-edge solutions that adapt to evolving threats in poker, strategy games, and other competitive gaming environments.

We are seeking a Principal Architect, a hands-on technical manager who will oversee the end-to-end anti-cheat technical pipeline, ensuring scalable, real-time detection. This role will focus on the development, deployment, implementation, and integration of AI models into production environments, working closely with leadership, product, data scientists, ML engineers, and application developers to ensure seamless operation and enforcement of security measures.

Key Responsibilities

Game Integrity & AI Research

• Develop and deploy machine learning models to detect collusion, BOT / AI-assisted play, and other forms of cheating in online poker.
• Leverage game theory, behavioral analytics, neural networks, , and deep reinforcement learning to identify unfair play patterns.
• Design adversarial AI strategies to stress-test poker security models and proactively identify vulnerabilities.
• Our current solution is based on a foundation neural network

Automation & Bot Detection

• Develop real-time bot detection models that analyze mouse movements, timing patterns, and decision consistency to differentiate human players from AI-assisted or fully automated bots.
• Use keystroke dynamics, clickstream analysis, and behavioral biometrics to detect robotic play.
• Research multi-accounting automation and ring-based bot networks, developing AI-driven countermeasures.
• Implement graph-based network analysis to uncover bot farms and shared automation systems.

Game Theory & Exploitative Modeling

• Research and implement game-theoretic AI models to analyze deviations from Nash equilibrium and identify potential cheating behaviors.
• Develop exploitative modeling techniques to compare player behavior against optimal strategies and detect unnatural patterns.
• Utilize inverse reinforcement learning to infer player intent and detect deviations from expected game dynamics.
• Build multi-agent simulations to test different cheating scenarios and AI-driven countermeasures.

Requirements:

-Technical Skills

• PhD or Master’s in Computer Science, Machine Learning, Statistics, Mathematics, or a related field.
• 4+ years of experience in neural networks, deep reinforcement learning , preferably in gaming, fraud detection, cybersecurity, or fintech.
• Strong programming skills in Python, SQL, and distributed computing frameworks (Spark, Hadoop, or similar).
• Experience with TensorFlow, PyTorch, or Scikit-learn for ML model development.
• Hands-on experience deploying ML models in cloud environments (AWS, GCP, Azure) and optimizing for low-latency inference.
• Strong foundation in game theory, Nash equilibrium, and multi-agent learning.
• Familiarity with bot detection methods, anti-automation models, and behavioral fingerprinting.
• Experience working with large-scale structured and unstructured data to detect patterns and anomalies.
• Proficiency in MLOps, CI/CD for AI models, and real-time fraud detection pipelines.

-Preferred Experience

• Experience working with real-time fraud detection systems in gaming, cybersecurity, or financial technology.
• Understanding of multi-accounting fraud, bot networks, and adversarial machine learning.
• Experience with graph analytics, Bayesian inference, and behavioral clustering for adversarial behavior modeling.
• Strong analytical and problem-solving skills, with a passion for ensuring fairness in online gaming.

Prior work with multi-agent reinforcement learning (MARL) systems or inverse reinforcement learning (IRL) is a plus.

Responsibilities

• Analyze raw data: assessing quality, cleansing, structuring for downstream processing
• Design accurate and scalable prediction algorithms
• Collaborate with engineering team to bring analytical prototypes to production
• Generate actionable insights for business improvements

Qualifications

• Bachelor's degree or equivalent experience in quantative field (Statistics, Mathematics, Computer Science, Engineering, etc.)
• At least 1 - 2 years' of experience in quantitative analytics or data modeling
• Deep understanding of predictive modeling, machine-learning, clustering and classification techniques, and algorithms
• Fluency in a programming language (Python, C,C++, Java, SQL)
• Familiarity with Big Data frameworks and visualization tools (Cassandra, Hadoop, Spark, Tableau)