Staff Data Scientist
This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Staff Data Scientist based in the United States.
This role sits at the core of a large-scale AI-powered fraud detection platform, where data science directly protects digital trust across hundreds of global customers. You will design and own advanced machine learning systems that analyze billions of real-world events to detect and prevent sophisticated fraud and abuse patterns. The environment is highly technical and adversarial, requiring strong statistical depth and a deep understanding of security-driven data patterns. You will work closely with ML engineers, platform teams, and fraud experts to translate evolving attacker behaviors into robust, production-grade models. This is a high-impact role where your insights directly shape model architecture, feature engineering strategy, and system resilience. You will operate in a fast-moving, research-driven setting where experimentation, rigor, and production accountability are equally critical. Your work will directly reduce financial losses, improve detection accuracy, and strengthen platform trust at scale.
Accountabilities:
In this role, you will lead the design, development, and optimization of advanced machine learning models that detect fraud and abuse across massive, high-velocity datasets. You will operate at the intersection of statistics, security, and production engineering, ensuring models remain resilient against evolving adversarial behavior.
- Architect and own advanced machine learning strategies for fraud detection, including payment fraud, identity abuse, account takeover, and network manipulation
- Translate complex fraud and security signals into scalable modeling approaches that balance accuracy, robustness, and business impact
- Design and maintain production-grade feature engineering pipelines informed by deep understanding of attacker behavior and system vulnerabilities
- Establish model evaluation, monitoring, and diagnostic frameworks to detect performance degradation, data drift, and adversarial adaptation
- Lead experimentation and statistical research to uncover new fraud patterns and validate signal effectiveness in production environments
- Partner with ML engineers and security teams to build adversarially robust systems and ensure seamless model deployment and performance
- Leverage AI tools to accelerate experimentation, automate analysis workflows, and improve modeling efficiency while maintaining statistical rigor
- 5+ years of hands-on data science or machine learning experience with ownership of production models at scale
- Strong domain expertise in fraud, cybersecurity, or adversarial systems (e.g., payment fraud, identity abuse, account takeover, network attacks)
- Advanced understanding of statistical modeling, including bias-variance tradeoffs, hypothesis testing, and model diagnostics
- Experience with multiple ML paradigms including tree-based models (XGBoost, LightGBM), deep learning (CNNs, RNNs, transformers), and graph-based methods (GNNs)
- Proven ability to diagnose production model failures caused by drift, adversarial adaptation, or feature leakage
- Strong programming skills in Python and experience working with large-scale data environments
- Ability to translate ambiguous fraud problems into structured modeling and experimentation frameworks
- Experience using AI tools (LLMs, AutoML, or similar) to accelerate feature engineering and analysis while maintaining validation rigor
- Advanced degree in a quantitative field (or equivalent industry experience with deep statistical modeling exposure) preferred
- Competitive compensation with performance-based incentives
- Equity opportunities in a high-growth AI company
- Comprehensive health, dental, and vision insurance
- Flexible remote work environment across the United States
- Opportunities to work on large-scale, real-world fraud and security problems
- Strong learning culture with exposure to advanced ML, AI, and security domains
- Collaborative environment with ML experts, engineers, and fraud specialists
- Career growth in a high-impact, research-driven data science organization.
Requirements
This role requires deep expertise in statistical modeling, machine learning, and fraud/security domains, combined with strong production experience and the ability to operate in adversarial environments.