Senior Data Analyst, Risk Analytics

SeatGeek is a technology company modernizing the ticketing industry, and it is seeking a Senior Data Analyst for its Risk Analytics team. The role leads fraud analytics strategy by building models, running statistical experiments, developing data pipelines and dashboards, evaluating vendors, monitoring risk metrics, and applying AI-assisted workflows to improve fraud prevention.

Responsibilities:

• Build and maintain Python-based analyses, models, and data pipelines that support fraud decisioning, vendor evaluation, and internal risk scoring
• Design and run statistical experiments from hypothesis through measurement and communication of results, including A/B tests on routing changes, holdout experiments, and vendor performance assessments
• Develop and iterate on internal fraud risk models using SeatGeek transaction and vendor data; own model calibration, validation, and ongoing performance monitoring
• Actively use AI tools including LLMs, code generation, and agentic workflows to move faster and build smarter; help define how AI gets embedded into the team's analytical processes, and identify opportunities to automate work currently done manually
• Contribute to vendor performance analysis: assess score calibration, measure lift across segments, and surface findings that inform routing decisions and contract discussions
• Build and maintain dashboards and reports in Looker and Hex; develop SQL models and data views to support the team's analytical needs
• Monitor fraud and operations metrics, investigate anomalies, and escalate findings with a clear point of view on recommended actions
• Collaborate with Risk Ops agents, the manager, and cross-functional partners in Engineering, Payments, and CX to translate analysis into action

Requirements:

• 3+ years of experience in fraud analytics, risk, fintech, or a quantitatively demanding analytical role
• Strong Python skills; you build end-to-end analyses and pipelines independently, and are proficient with pandas, scikit-learn, statsmodels, or equivalent libraries
• Strong SQL; you can own complex data pulls, understand warehouse structures, and build views and models that others rely on
• Solid statistical grounding: you can design statistically valid experiments, perform significance testing, assess model calibration, and communicate findings clearly to a non-technical audience
• Hands-on experience building, training, and validating classification models independently; familiarity with model evaluation methods, handling class imbalance, and translating model outputs into business decisions
• Genuine enthusiasm for AI tools: you actively use LLMs and code generation in your day-to-day work, think about how to design AI-assisted workflows, and take initiative in identifying where AI can replace manual effort
• Comfort operating in ambiguity; you are expected to define the problem as much as solve it
• Familiarity with fraud vendors such as Forter, Riskified, or Sardine is a plus; experience with Looker or similar BI tools is a plus