Job DescriptionJob Description
StubHub is on a mission to redefine the live event experience on a global scale. Whether someone is looking to attend their first event or their hundredth, we're here to delight them all the way from the moment they start looking for a ticket until they step through the gate. The same goes for our sellers. From fans selling a single ticket to the promoters of a worldwide stadium tour, we want StubHub to be the safest, most convenient way to offer a ticket to the millions of fans who browse our platform around the world.
The Role
We're seeking a Senior Data Scientist to lead the science behind a best-in-class ticketing experience for fans, with a focus on the operational journey from ticket purchase through event entry. In this role, you will own and develop predictive and decisioning models that proactively identify and mitigate fulfillment issues, strengthen inventory validation, and optimize customer service policies — all while balancing fan experience with operational constraints.
You will work on problems where getting it right matters: predicting issues before they impact fans, identifying emerging pain points at scale, and turning moments of potential failure into opportunities to build trust and loyalty. This includes building and productionizing models on both structured and unstructured data, such as LLM-backed pipelines that extract actionable signals from customer communications and support interactions.
You will partner closely with product managers, analytics engineers, operations leaders, and other data scientists to translate ambiguous business problems into durable, production-ready data products, and to influence decisions that measurably improve the fan experience.
Location: Hybrid (3 days in office/2 days remote) – New York, NY or Century City, CA
What You'll Do
- Own the science behind ticket fulfillment: Drive reliability, ease of use, and customer satisfaction by crafting and deploying scalable, production-grade machine learning models that directly inform operational systems and decisions.
- Drive data-informed strategy: Work with operations partners to shape roadmaps, using analysis and modeling to identify, prioritize, and size high-impact opportunities that can be implemented and sustained at scale.
- Design for validation: Apply principles of experimentation and causal inference to ensure work products can be rigorously evaluated, defining offline validation and online testing strategies early in the design process.
- Build the data foundation: Partner with platform and analytics teams to ensure data availability and quality, including event instrumentation, batch and streaming ETL, feature stores, and monitoring for model performance, bias, and drift.
- Tell the story: Communicate trade-offs and impact to execs and non-technical partners; make the complex understandable and actionable.
What You've Done
- 5+ years of industry experience in data science or machine learning, with an MS or PhD in mathematics, statistics, computer science, or a related quantitative field .
- Strong programming skills in Python, with experience using numerical and machine learning libraries such as Pandas, NumPy, SciPy, scikit-learn, and gradient-boosting frameworks (e.g., LightGBM, XGBoost).
- Demonstrated experience building, deploying, and iterating on production machine learning models in cloud environments (e.g., AWS, Azure), including post-deployment monitoring and improvement.
- Expertise working with large-scale data using modern analytics and compute platforms such as Snowflake, BigQuery, or Databricks, with strong proficiency in SQL.
- Proven ability to establish data science methodology in new or ambiguous domains, owning work end to end—from stakeholder alignment and problem framing to delivery and measurable impact.
- Excellent communication skills, with the ability to clearly articulate modeling assumptions, tradeoffs, and impact to both technical and non-technical audiences.
Nice to have:
- Experience applying machine learning to operational problem spaces such as ticket fulfillment, fraud detection, customer service, or trust and safety.
- Experience with production ML platforms and workflows, such as Metaflow or comparable systems (e.g., Airflow-based ML pipelines, Kubeflow, SageMaker Pipelines, Prefect, Flyte), including model versioning, scheduling, and monitoring.
- Experience selecting and applying appropriate causal inference approaches to evaluate model and policy impact, including methods such as uplift modeling, synthetic control, and BSTS.
What We Offer
- Accelerated Growth Environment: An environment designed for swift skill and knowledge enhancement, where you have the autonomy to lead experiments and tests on a massive scale.
- Top Tier Compensation Package: Competitive base, equity, and upside that tracks with your impact.
- Flexible Time Off: Enjoy unlimited Flex Time Off, giving you the flexibility to manage your